A UAV swarm target tracking method based on observer and hierarchical network

Abstract

This invention discloses a method for tracking drone swarm targets based on observers and a hierarchical network. The method includes the following steps: 1) dividing the drones in a drone swarm into three roles: leader, follower, and observer; N drones form a multi-agent system, in which each drone acts as an independent agent. The multi-agent system, through a leader-follower-observer model, is responsible for forming an orderly formation for the entire drone swarm; 2) introducing a two-layer joint drone network model to establish a flying ad hoc network responsible for communication in drone swarm target tracking; 3) after the drone swarm achieves formation control, it performs target tracking to effectively track single or multiple targets. This invention introduces the concept of observers to achieve effective formation control of the swarm, enabling the drone swarm to have a more comprehensive understanding of its surroundings and make corresponding adjustments in a timely manner, thereby improving the overall mobility and flexibility of the drone swarm.

Description

Technical Field

[0001] The present invention relates to unmanned aerial vehicle (UAV) control technology, and in particular to an UAV cluster target tracking method based on an observer and a hierarchical network. Background Art

[0002] The technical practices in existing research in the field of modern drone target tracking are facing challenges at the application level. First, the images captured by drones are affected by the complexity of their observation environment. Coupled with the changes in relative motion between the drone and the monitored object, it is easy for the target to disappear in the captured image, making the tracking task difficult to sustain. Secondly, data synchronization and communication delay issues between multiple drones also have a negative impact on collaborative efficiency and accuracy, resulting in lower adaptability, tracking efficiency, and real-time feedback capabilities when dealing with complex environments. To address these issues, a drone cluster target tracking method is needed to achieve stable tracking of fast-moving targets or targets in complex backgrounds and significantly improve tracking efficiency. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a UAV cluster target tracking method based on observers and hierarchical networks in response to the defects in the existing technology.

[0004] The technical solution adopted by the present invention to solve the technical problem is: a method for tracking a target of a UAV cluster based on an observer and a hierarchical network, comprising the following steps:

[0005] 1) Divide the drones in a drone swarm into three roles: leader, follower, and observer;

[0006] The leader is responsible for guiding the movement direction and speed of the entire swarm, planning the path based on the preset tasks or dynamic goals in the environment, and passing instructions to followers and observers;

[0007] The follower forms a convex hull around the leader based on a preset reference point and adjusts its position and speed according to the leader's instructions. The relative position between the follower and the leader changes, but the distance remains unchanged;

[0008] The observer is responsible for monitoring changes in the environment, including the appearance of obstacles or other potential threats. When the observer detects environmental changes, it sends data information to the leader and followers.

[0009] The observer's position is dynamically adjusted as the leader and follower clusters move, and is placed in a position that provides maximum coverage of the drone cluster's surroundings so that changes can be detected in a timely manner;

[0010] N unmanned aerial vehicles (UAVs) form a multi-agent system. In the system, each UAV acts as an independent agent. The multi-agent system is responsible for the formation of an orderly formation of the entire UAV swarm through the leader-follower-observer model.

[0011] 2) Introducing a two-layer joint UAV network model to establish flying ad hoc networks (FANETs) responsible for communication in UAV swarm target tracking;

[0012] Use heterogeneous architecture based on SDN wireless defined network for reliable communication in flight ad hoc network;

[0013] The drone swarm is divided into a controller, an upper drone layer, and a lower drone layer; the upper drone layer is responsible for performing mobility estimation and prediction operations and working with the controller to make routing decisions, while the lower drone layer is responsible for performing ground or air search missions or providing services;

[0014] The upper UAV layer includes the cluster head UAV CHU, and the lower UAV layer includes the cluster member UAV CMU; one cluster head UAV manages multiple cluster member UAVs;

[0015] Each drone is equipped with a global navigation satellite system for obtaining drone location data;

[0016] Calculate the Euclidean distance between drones;

[0017] The position coordinates of UAV c and UAV i at time t;

[0018] Each UAV communicates with its neighboring UAVs through its UAV address identification. The controller estimates the transmission routing cost of each UAV request. The controller calculates the optimal routing path for the cluster head UAV based on the global network information;

[0019] 3) After achieving formation control, drone swarms can track targets. Using an ant colony algorithm, they simulate the collective behavior of ants to effectively track single or multiple targets. This utilizes the swarm intelligence of drones, information exchange, and collaborative control to improve tracking accuracy and efficiency.

[0020] According to the above scheme, in step 1), each drone acts as an independent intelligent entity, equipped with a high-performance processor, sensor and wireless communication module.

[0021] According to the above scheme, in step 1), each UAV acts as an independent intelligent entity and obtains its own position by being equipped with a navigation and positioning system.

[0022] According to the above scheme, in step 2), the Euclidean distance between the UAV c and the adjacent UAV i in the formation is expressed as:

[0023]

[0024] in( , , )and( , , ) represent the position coordinates of UAV c and UAV i at time t respectively.

[0025] According to the above scheme, in step 2), the controller calculates the optimal routing path for the cluster head UAV based on the global network information; the details are as follows:

[0026] The extended Kalman filter (EKF) is used to accurately estimate and predict the mobility of UAVs. The cluster head UAVs (CHUs) control their corresponding cluster member UAVs (CMUs) and calculate and output the global optimal path through the DPSO routing decision algorithm to improve communication efficiency.

[0027] According to the above scheme, in step 2), each drone communicates with its neighboring drones through its drone address identification, as follows:

[0028] Through the collaborative work of the central controller and cluster head drones, routing decisions are made and communication is carried out;

[0029] In the MAC architecture, the entire drone swarm shares spectrum resources through orthogonal frequency division multiple access (OFDMA). Cluster head drones (CHUs) use IEEE 802.11p on a dedicated channel for H2H communication. The cluster head drone (CHU) and cluster member drones (CMUs) use LTE for H2M communication. Cluster member drones (CMUs) use IEEE802.11p that complies with the EDCF standard for M2M communication, achieving high-quality communication connections.

[0030] According to the above solution, in step 3), tracking of single or multiple targets is achieved by simulating the collective behavior of ants based on the ant colony algorithm.

[0031] According to the above scheme, in step 3), tracking of a single or multiple targets is achieved;

[0032] 3.1) For single target tracking, the drone’s behavior strategy is as follows:

[0033] When all drones fail to sense the target, they act in a cluster-controlled manner and move toward a virtual target point according to predetermined rules or pre-set paths.

[0034] If some drones sense the target, they will begin to adjust their behavior, maintain a certain distance from other drones, and move toward the perceived target position. Other drones that have not sensed the target will adjust their behavior by observing the movement status of surrounding drones, and finally converge to achieve the purpose of consistent tracking.

[0035] 3.2) For multi-target tracking, the drone’s behavior strategy is as follows:

[0036] When a drone senses a single target, the drone swarm quickly gathers and matches the target's moving speed to adjust its speed to track the target;

[0037] When a drone senses multiple targets, the drone group quickly separates and forms different sub-groups, each of which tracks different targets. Other drones that have not sensed any targets will decide to voluntarily follow the sub-group with target information through information interaction.

[0038] The beneficial effects produced by the present invention are:

[0039] 1. This invention introduces the concept of observers to achieve effective formation control of the swarm. The leader serves as the navigation core, leading the overall direction, and the followers follow the leader to perform tasks. At the same time, the rational arrangement of observer nodes enables the drone swarm to have a more comprehensive understanding of the surrounding environment and make corresponding adjustments in a timely manner, so that the drone swarm maintains a tighter and more orderly formation when performing tasks, improving overall maneuverability and flexibility.

[0040] 2. The present invention optimizes the communication loss problem in the drone cluster control network. By designing a two-layer joint drone network technology, it avoids problems such as inefficient path discovery, excessive hops, and lengthy paths. It makes optimal routing decisions based on global information, improves communication efficiency, and achieves high-quality communication connections. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0042] Figure 1 is a flow chart of a method according to an embodiment of the present invention;

[0043] Figure 2 Schematic diagram of the process of forming a convex hull between a leader and a follower according to an embodiment of the present invention;

[0044] Figure 3 A flowchart of the steps of single and multiple target tracking according to an embodiment of the present invention;

[0045] Figure 4 A schematic diagram of single target trajectory tracking according to an embodiment of the present invention;

[0046] Figure 5 Schematic diagram of multi-target tracking and capture according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0048] like Figure 1 As shown in FIG, a method for tracking a target of a UAV cluster based on an observer and a hierarchical network includes the following steps:

[0049] 1) Divide the drones in a drone swarm into three roles: leader, follower, and observer;

[0050] The leader is responsible for guiding the movement direction and speed of the entire swarm, planning the path based on the preset tasks or dynamic goals in the environment, and passing instructions to followers and observers;

[0051] The follower forms a convex hull around the leader based on a preset reference point and adjusts its position and speed according to the leader's instructions. The relative position between the follower and the leader changes, but the distance remains unchanged;

[0052] In this embodiment, Figure 2 , the follower takes the leader as the center point and changes into the desired geometric shape over time. The follower forms a convex hull around the leader and adjusts its position and speed according to the leader's instructions.

[0053] The observer is responsible for monitoring changes in the environment, including the appearance of obstacles or other potential threats. When the observer detects environmental changes, it sends data information to the leader and followers.

[0054] N unmanned aerial vehicles (UAVs) form a multi-agent system. In this system, each UAV acts as an independent agent, equipped with high-performance processors, sensors, and wireless communication modules to support complex network protocols and algorithms. It uses the Beidou Navigation System (BNS) to obtain noisy positions. The multi-agent system introduces a leader-follower-observer model to form an orderly formation for the entire UAV swarm. It also implements low-level control to ensure that the UAV cluster achieves the desired formation tracking when tracking targets.

[0055] The concept of observers is introduced to achieve effective formation control of the swarm. The leader, as the navigation core, leads the overall direction, while the followers follow the leader to carry out the mission. At the same time, the rational arrangement of observer nodes enables the drone swarm to have a more comprehensive understanding of the surrounding environment and make corresponding adjustments in a timely manner, allowing the drone swarm to maintain a tighter and more orderly formation when carrying out the mission, improving overall maneuverability and flexibility.

[0056] 2) Introducing a two-layer joint UAV network model to establish flying ad hoc networks (FANETs) responsible for communication in UAV swarm target tracking;

[0057] Use heterogeneous architecture based on SDN wireless defined network for reliable communication in flight ad hoc network;

[0058] Divide the drone swarm into a controller, an upper drone layer, and a lower drone layer;

[0059] The upper UAV layer includes the cluster head UAV CHU, and the lower UAV layer includes the cluster member UAV CMU;

[0060] Each drone is equipped with a global navigation satellite system for obtaining drone location data;

[0061] Calculate the Euclidean distance between drones;

[0062] The Euclidean distance between UAV c and its adjacent UAV i in the formation is expressed as:

[0063]

[0064] in( , , )and( , , ) represent the position coordinates of UAV c and UAV i at time t respectively.

[0065] Each UAV communicates with its neighboring UAVs through its UAV address identification. The controller estimates the transmission routing cost of each UAV request. The controller calculates the optimal routing path for the cluster head UAV based on the global network information;

[0066] The central controller and cluster-head UAVs work together to make routing decisions and conduct communication. In the MAC architecture, the entire UAV swarm shares spectrum resources using Orthogonal Frequency Division Multiple Access (OFDMA). Cluster-head UAVs (CHUs) use dedicated IEEE 802.11p channels for H2H communication. H2M communication between the CHUs and cluster member UAVs (CMUs) uses LTE. M2M communication between cluster member UAVs (CMUs) follows the IEEE 802.11p EDCF standard, achieving high-quality communication connectivity. An extended Kalman filter (EKF) is used to accurately estimate and predict the mobility of UAVs. CHUs control their corresponding CMUs to select appropriate routing paths. The DPSO routing decision algorithm calculates and outputs the globally optimal path to improve communication efficiency.

[0067] 3) After achieving formation control, drone swarms can conduct target tracking, effectively tracking single or multiple targets. This leverages the intelligent nature of drone swarms, using information exchange and collaborative control to improve tracking accuracy and efficiency.

[0068] In step 3), the tracking of single or multiple targets is achieved by simulating the collective behavior of ants based on the ant colony algorithm.

[0069] like Figure 3 As shown, there are two cases: single target tracking and multi-target tracking:

[0070] 3.1) For single target tracking, the drone’s behavior strategy is as follows:

[0071] like Figure 4 As shown in the figure, when all drones fail to sense the target, they act in a cluster control manner and move toward a virtual target point according to predetermined rules or pre-set paths.

[0072] If some drones sense the target, they will begin to adjust their behavior, maintain a certain distance from other drones, and move toward the perceived target position. Other drones that have not sensed the target will adjust their behavior by observing the movement status of surrounding drones, and finally converge to achieve the purpose of consistent tracking.

[0073] 3.2) For multi-target tracking, the drone’s behavior strategy is as follows:

[0074] like Figure 5 As shown in the figure, when a drone senses a single target, the drone swarm quickly gathers and matches the target's moving speed to adjust the speed to track the target;

[0075] When a drone senses multiple targets, the drone group quickly separates and forms different sub-groups, each of which tracks different targets. Other drones that have not sensed any targets will decide to voluntarily follow the sub-group with target information through information interaction.

[0076] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. A method for tracking target of UAV cluster based on observer and hierarchical network, characterized by: The following steps are involved: 1) Divide the drones in a drone swarm into three roles: leader, follower, and observer; The leader is responsible for guiding the movement direction and speed of the entire swarm, planning the path based on the preset tasks or dynamic goals in the environment, and passing instructions to followers and observers; The follower forms a convex hull around the leader based on the preset reference point and adjusts its position and speed according to the leader's instructions. The relative position between the follower and the leader changes, but the distance remains unchanged; The observer is responsible for monitoring changes in the environment, including the appearance of obstacles or other potential threats. When the observer detects environmental changes, it sends data information to the leader and followers. The observer's position is dynamically adjusted as the leader and follower clusters move, and is placed in a position that provides maximum coverage of the drone cluster's surroundings so that changes can be detected in a timely manner; N drones form a multi-agent system. In the system, each drone acts as an independent agent. The multi-agent system is responsible for forming an orderly formation of the entire drone group through the leader-follower-observer model. 2) Introducing a two-layer joint UAV network model to establish flying ad hoc networks (FANETs) responsible for communication in UAV swarm target tracking; Use heterogeneous architecture based on SDN wireless defined network for reliable communication in flight ad hoc network; The drone swarm is divided into a controller, an upper drone layer, and a lower drone layer; the upper drone layer is responsible for performing mobility estimation and prediction operations and working with the controller to make routing decisions, while the lower drone layer is responsible for performing ground or air search missions or providing services; The upper UAV layer includes the cluster head UAV CHU, and the lower UAV layer includes the cluster member UAV CMU; one cluster head UAV manages multiple cluster member UAVs; Calculate the Euclidean distance between drones; Each UAV communicates with its neighboring UAVs through its UAV address identification. The controller estimates the transmission routing cost of each UAV request. The controller calculates the optimal routing path for the cluster head UAV based on the global network information; 3) After the drone swarm achieves formation control, it conducts target tracking to effectively track single or multiple targets.

2. The method for tracking target of UAV cluster based on observer and hierarchical network according to claim 1 is characterized in that: In step 1), each drone acts as an independent intelligent entity, equipped with a high-performance processor, sensors, and wireless communication modules.

3. The method for tracking target of UAV cluster based on observer and hierarchical network according to claim 1 is characterized in that: In step 1), each UAV acts as an independent intelligent entity and obtains its own position by being equipped with a navigation and positioning system.

4. The method for tracking target of UAV cluster based on observer and hierarchical network according to claim 1, characterized in that: In step 2), the Euclidean distance between the UAV c and the adjacent UAV i in the formation is expressed as: in( , , )and( , , ) represent the position coordinates of UAV c and UAV i at time t respectively.

5. The method for tracking target of UAV cluster based on observer and hierarchical network according to claim 1 is characterized in that: In step 2), the controller calculates the optimal routing path for the cluster head UAV based on the global network information; specifically, as follows: The extended Kalman filter is used to accurately estimate and predict the mobility of UAVs. The cluster head UAVs (CHUs) control their corresponding cluster member UAVs (CMUs) and calculate and output the global optimal path through the DPSO routing decision algorithm to improve communication efficiency.

6. The method for tracking target of UAV cluster based on observer and hierarchical network according to claim 1, characterized in that: In step 2), each drone communicates with its neighboring drones through its drone address identification, as follows: Through the collaborative work of the central controller and cluster head drones, routing decisions are made and communication is carried out; In the MAC architecture, the entire drone swarm shares spectrum resources through orthogonal frequency division multiple access. Cluster head drones use IEEE 802.11p with dedicated channels for H2H communication, cluster head drones use LTE for H2M communication with cluster member drones, and cluster member drones use IEEE 802.11p that complies with the EDCF standard for M2M communication, achieving high-quality communication connections.

7. The method for tracking target of UAV cluster based on observer and hierarchical network according to claim 1, characterized in that: In step 3), tracking of single or multiple targets is achieved by simulating the collective behavior of ants based on the ant colony algorithm.

8. The method for tracking target of UAV cluster based on observer and hierarchical network according to claim 1, characterized in that: In step 3), tracking of a single or multiple targets is achieved; 3.1) For single target tracking, the drone’s behavior strategy is as follows: When all drones fail to sense the target, they act in a swarm-controlled manner, moving toward a virtual target point according to predetermined rules or pre-set paths; If some drones sense the target, they will begin to adjust their behavior, maintaining a certain distance from other drones while moving toward the perceived target. Other drones that have not sensed the target will adjust their behavior by observing the movement of surrounding drones, and finally converge to achieve the goal of consistent tracking. 3.2) For multi-target tracking, the drone’s behavior strategy is as follows: When a drone senses a single target, the drone swarm quickly gathers and matches the target's moving speed to adjust its speed to track the target; When a drone senses multiple targets, the drone group quickly separates and forms different sub-groups, each of which tracks different targets. Other drones that have not sensed any targets will decide to voluntarily follow the sub-group with target information through information interaction.

Images