An underwater robot cluster formation motion and experimental method architecture

Abstract

The application discloses an underwater robot cluster formation motion and experiment method, and belongs to the underwater robot cluster formation motion field; steps include: establishing an individual virtual force control model of the underwater robot cluster; establishing a local perception information model of the individual underwater robot, and acquiring three-dimensional relative distance and azimuth information of the individual underwater robot and neighbor underwater robots; based on the virtual force control model and the local perception information model, an expected underwater robot cluster formation is obtained through adjustment; underwater robot cluster formation motion experiment is carried out in an open water area; based on experimental data collection, underwater robot cluster formation completion degree calculation is carried out to verify the underwater robot cluster formation effect. The application solves the problems that when the cluster motion using the global information interaction technology to realize communication is applied to the underwater environment, it is difficult to obtain accurate distance and azimuth information to complete the formation task and the like.

Description

Technical Field

[0001] The present invention belongs to the field of underwater robot cluster formation motion, and in particular relates to an underwater robot cluster formation motion and an experimental method. Background Art

[0002] In nature, many organisms develop or evolve as populations, achieving coordinated movement through local interactions. For example, schools of fish often swim in cylindrical groups to avoid predators. Many fish rely on visual observation of their neighbors to achieve collective coordinated movement. This behavior does not require any explicit communication mechanisms, but rather spontaneously generates collective responses based on local sensory information. This local information-based swarming mechanism provides important biological insights for the control of multi-agent systems.

[0003] Existing multi-agent swarm control methods primarily include behavior-based methods, leader-follower methods, virtual structure methods, and artificial potential field methods. These methods have been widely applied to multi-agent swarm motion. For example, behavior-based methods achieve overall swarm motion by defining interaction rules between individuals; leader-follower methods rely on guidance from a specific individual (the leader), with other individuals following the leader's instructions; virtual structure methods construct a virtual overall structure to guide the movement of the individuals; and artificial potential field methods achieve swarm motion by designing potential field functions, driving the individuals under the potential field.

[0004] However, existing research on multi-agent swarm control has mostly relied on global information exchange between robots. For example, when aerial drone swarms form specific swarm operations, they typically rely on a central controller and a global positioning system (GPS) to acquire and exchange neighboring location information in real time. This reliance on global information works well in open environments with good communication conditions. However, in practical applications, particularly underwater environments, multi-agent formation control methods that rely on global information and positioning are difficult to apply due to limited communication. Signal propagation is limited in underwater environments, and communication delays and packet loss are common, making control methods based on global information a significant challenge. Summary of the Invention

[0005] Technical issues to be solved:

[0006] To overcome the shortcomings of existing technologies, the present invention draws on the fact that schools of fish achieve efficient cluster movement through local visual observation of their neighbors. This invention provides an underwater robot cluster formation movement and experimental method. This method establishes an underwater robot cluster formation model based on a virtual force model and local visual perception information, and achieves orderly cluster movement by simulating the virtual force interaction between individuals. Furthermore, based on the Yolox model with an added attention mechanism and the binocular ranging principle, the relative distance and orientation information of the underwater robot's neighbors is acquired, providing local perception information for cluster formation. Finally, a deployment planning method for underwater robot cluster movement experiments is established, and cluster formation experiments are evaluated using a formation completion index. This invention addresses the problem that cluster movement using global information interaction technology to achieve communication is difficult to obtain accurate distance and orientation information to complete formation tasks when applied to underwater environments.

[0007] The technical solution of the present invention is: an underwater robot cluster formation movement and experimental method, the specific steps are as follows:

[0008] Establish an individual virtual force control model for the underwater robot cluster, set up a formation motion model for N underwater robots, and update the position of individual underwater robots by obtaining the direction and magnitude of the resultant force of N underwater robots;

[0009] A local perception information model for an individual underwater robot is established. Based on the target detection model, the ORB feature extraction and matching method is used to obtain the three-dimensional relative distance and orientation information between the individual underwater robot and its neighboring underwater robots.

[0010] Based on the virtual force control model and the local perception information model, the desired underwater robot cluster formation is obtained through adjustment;

[0011] Conduct underwater robot swarm formation movement experiments in open water;

[0012] Based on the experimental collected data, the completion degree of underwater robot cluster formation is calculated to verify the achievement of underwater robot cluster formation effect.

[0013] A further technical solution of the present invention is: the individual virtual force control model includes individual underwater robot repulsion and individual underwater robot attraction; when the distance between adjacent robots is less than the expected relative distance, the robots exert repulsion on each other, and the repulsion increases as the distance decreases to avoid robot collision; when the distance between the robots is greater than the expected distance, the robots exert attraction between each other, attract each other, and tend to the set expected position, and finally maintain a fixed distance to stably form a cluster.

[0014] A further technical solution of the present invention is: the method for obtaining the resultant force of the N underwater robots is that an individual underwater robot obtains the first-order derivative of the distance to its neighbor robots, and then sums the derivatives of the distances to all neighbors to obtain all the resultant forces with all neighbors.

[0015] A further technical solution of the present invention is: the position update rule of the individual underwater robot is:

[0016]

[0017] Where N is the total number of underwater robots, d is the relative distance between adjacent underwater robots, and d t is the expected relative distance, q ij is the relative position of adjacent underwater robots; a is the variable defining the repulsive force, and b is the variable defining the attractive force.

[0018] A further technical solution of the present invention is: the local perception information model includes a yolox target detection model and a binocular distance and orientation estimation model;

[0019] The binocular camera in the binocular distance and orientation estimation model is used to obtain the underwater robot's multiple motion modal image data as a sample data set;

[0020] Input the sample data set into the Yolox target detection model and output the position coordinates of the neighbor underwater robot on the image;

[0021] The binocular distance and orientation estimation model adopts the ORB feature extraction and matching method to obtain the disparity of the binocular left and right views within the target detection frame on the image. Based on the binocular ranging principle, the obtained disparity is used to calculate the three-dimensional relative distance and orientation information of the neighboring underwater robot.

[0022] A further technical solution of the present invention is: a coordinated attention mechanism is set in the backbone feature extraction network of the yolox target detection model, and the dependencies between data channels and spatial dimensions are captured simultaneously through the coordinated attention mechanism, thereby increasing the global perception ability of the model and maintaining the real-time performance of the model calculation.

[0023] A further technical solution of the present invention is: the experimental method for conducting underwater robot cluster formation movement in open water is:

[0024] Calibrate the binocular vision system of each underwater robot and check that each underwater robot is in normal condition;

[0025] Arrange the underwater robots in sequence in the designated waters, initialize the underwater robot cluster formation, plan the starting position and desired formation of the underwater robot cluster, and mark the pilot robot and follower robot;

[0026] Start the underwater robot control system, perform necessary preliminary debugging, and use the perception system to identify and track the target; perform underwater robot cluster movement control according to the predetermined plan, set the cluster formation, and plan a reasonable formation layout;

[0027] After collecting data on various motion conditions of the test targets, the cluster formation experiment was completed, and all experimental equipment was recovered and its status checked.

[0028] A further technical solution of the present invention is: the method for calculating the completion degree of the underwater robot cluster formation is:

[0029] Assume that the theoretical position coordinates of the underwater robot on the plane are P i (x i ,y i ), the actual coordinate position of the cluster experiment drone is P i '(x i ',y i '), then the distance between the theoretical position and the actual position is

[0030] Calculate the individual completion degree g of the underwater robot i ,

[0031]

[0032] Where R is the distance deviation threshold between the given theoretical position and actual position of the underwater robot;

[0033] According to the individual completion degree g of the underwater robot i Calculate the formation completion degree G,

[0034]

[0035] An underwater robot cluster formation includes N underwater robots constituting the formation, namely, virtual force control models and local perception information models carried by the robots, wherein the relative positions between adjacent underwater robots are controlled by the virtual force control model, thereby completing motion control of the cluster formation; the relative distance and orientation information of adjacent underwater robots are obtained by the local perception information model; and the invention also includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the underwater robot cluster formation motion and experimental method.

[0036] A computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the underwater robot cluster formation movement and experimental method when executed.

[0037] Beneficial effects

[0038] The beneficial effects of the present invention are as follows: the present invention adopts a cluster formation motion model based on a virtual force model and local perception information, verifies the feasibility of this method in forming the desired formation through simulation experiments, and verifies the cluster formation algorithm on an underwater robot. The formation completion evaluation index is established based on the experimental results and experimental evaluation is conducted to further verify the effectiveness of the underwater robot in achieving the desired formation. At the same time, the present invention establishes a deployment planning method for large-scale cluster experiments in open waters, taking into account the requirements of experimental scenarios and experimental condition constraints, and provides a practical implementation path for underwater robot cluster experiments.

[0039] The present invention has been experimentally verified to be effective in establishing a cluster formation algorithm through modeling, simulation verification and open water experiments of underwater robot cluster motion, and completed the experimental task of forming a formation of 15 underwater manta ray-like robots on a lake. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 : Simulation results of the relative motion position of the underwater robot cluster self-organization;

[0041] Figure 2 : Simulation diagram of relative position change of underwater robot cluster self-organized movement;

[0042] Figure 3 : Simulation results of underwater robot cluster motion orientation;

[0043] Figure 4 : Result diagram of underwater robot cluster motion orientation error;

[0044] Figure 5 : Framework diagram of local perception method for underwater robots;

[0045] Figure 6 : Schematic diagram of the underwater robot's perception of its neighbors at different distances;

[0046] Figure 7 : Flowchart of deployment of open water swarm formation movement experiment;

[0047] Figure 8 : Schematic diagram of cluster formation completion calculation;

[0048] Figure 9 : Calculation of the completion of a cluster of 3 and 6 underwater robots;

[0049] Figure 10 : Calculation of the completion of a formation of 15 underwater robots. DETAILED DESCRIPTION

[0050] The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present invention, but should not be construed as limiting the present invention.

[0051] Based on existing research, when implementing multi-agent swarm control, most of them rely on global information exchange between robots. For example, when an aerial drone swarm forms a specific swarm operation form, it usually relies on a central controller and a global positioning system (GPS) to obtain and exchange the location information of neighbors in real time. This global information reliance is effective in an open environment with good communication conditions. However, in practical applications, especially underwater environments, due to limited communication, multi-agent formation control methods that rely on global information and positioning will be difficult to apply. The present invention provides an underwater robot swarm formation movement and experimental method, the specific steps are as follows:

[0052] Step 1: Establish an individual virtual force control model for the underwater robot cluster, set up a formation motion model for N underwater robots, and update the position of individual underwater robots by obtaining the direction and magnitude of the resultant force of N underwater robots;

[0053] Step 2: Establish a local perception information model for an individual underwater robot. Based on the target detection model, use the ORB feature extraction and matching method to obtain the 3D relative distance and orientation information between the individual underwater robot and its neighboring underwater robots.

[0054] Step 3: Based on the virtual force control model and the local perception information model, the desired underwater robot swarm formation is obtained through adjustment;

[0055] Step 4: Conduct underwater robot swarm formation movement experiments in open water;

[0056] Step 5: Based on the experimental data collected, the underwater robot cluster formation completion degree is calculated to verify that the underwater robot cluster formation effect is achieved.

[0057] An underwater robot cluster formation includes N underwater robots constituting the formation, namely, virtual force control models and local perception information models carried by the robots, wherein the relative positions between adjacent underwater robots are controlled by the virtual force control model, thereby completing motion control of the cluster formation; the relative distance and orientation information of adjacent underwater robots are obtained by the local perception information model; and the invention also includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the underwater robot cluster formation motion and experimental method.

[0058] A computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the underwater robot cluster formation movement and experimental method when executed.

[0059] Drawing on the behavioral mechanism of fish swarming based on visual observation of their neighbors, this paper utilizes the local visual perception of its neighbors by underwater robots to study and implement underwater robot swarm formation motion. Specifically, the paper first establishes an underwater robot swarm formation model based on a virtual force model and local visual perception information. By simulating the virtual forces between individuals, the paper achieves orderly swarm motion.

[0060] The above technical solution is further described below with reference to the accompanying drawings and examples:

[0061] In one embodiment, the underwater robot is a manta ray-like underwater robot. When swimming at low speeds, the manta ray-like robot exhibits high body stability, minimal swaying, strong maneuverability, and swimming efficiency. It is capable of performing complex maneuvers such as multi-degree-of-freedom motion, low-speed position retention, and direction reversal. These characteristics make the manta ray-like robot an ideal platform for studying underwater robot swarm motion. The specific steps of an underwater robot swarm formation motion and experimental method in this embodiment are as follows:

[0062] Step 1: Modeling and simulation of underwater robot swarm self-organizing motion

[0063] Inspired by the clustering behavior of certain groups in nature (fish schools, bird flocks, etc.), this paper controls the motion between robots by simulating the repulsive and attractive forces between adjacent robots based on a virtual force control model and a local perception information model.

[0064] Step 1.1: Build a swarm formation control model based on virtual force

[0065] In this embodiment, the virtual force control model is divided into two parts, repulsion and attraction. target When the distance d between the robots is greater than the desired distance, the robots exert a force of attraction, attracting them to the desired position, ultimately maintaining a fixed spacing and forming a stable cluster.

[0066] The total force F of all N neighbors ij is the Lennard-Jones potential V ij The average value of the resultant force is multiplied by the relative position q between robot i and its neighbor robot j. ij Determines the next movement p of robot ii The motion update rule of underwater robot i is expressed as,

[0067]

[0068] Where N is the total number of underwater robots, d is the relative distance between the underwater robot and its neighboring robots, and d t is the expected relative distance, q ij is the relative position of adjacent robots. Variable a defines the magnitude of the repulsive force, and variable b defines the magnitude of the attractive force. Using this formula, robot i updates its position based on the direction and magnitude of the resultant force, gradually adjusting to a stable desired formation.

[0069] In one embodiment, in order to achieve a stable desired formation, a triangle formation is used as the desired formation. This paper controls the movement based on the relative positions between the underwater robot and its neighbors, ensuring that the relative positions between the robots conform to the layout of the desired formation. By setting the desired position of each robot relative to its neighbors, a stable triangle formation is formed between the robot and the adjacent robots. If there are three robots i, j, and k, the desired distance between robot i and j is d target , the distance between robots i and k is also d target , and ∠ijk=60°, forming an equilateral triangle.

[0070] Step 1.2: Construct a local perception information model for underwater robots based on binocular vision

[0071] Reference Figure 5 As shown, in this embodiment, a Yolox target detection model with an added attention mechanism and a binocular distance and orientation estimation method are used to convert the image information of the neighbor underwater robot under binocular perception into three-dimensional relative distance and orientation information with the neighbor, providing local perception information for cluster formation control.

[0072] First, a binocular camera was used to capture image data of the underwater bionic robot in various motion modes (gliding, swooping, and diving). Each mode provides a different motion trajectory and perception angle. This acquisition of image data from multiple motion modes provides the perception system with information to accurately capture the characteristics of neighboring robots. The captured image data was also annotated with the "manta" category to create a dataset for training the detection model.

[0073] Next, to improve the detection model's accuracy in detecting neighboring targets, the present invention adds a Coordinate Attention mechanism to the Yolox backbone feature extraction network. This attention mechanism can simultaneously capture dependencies between data channels and in spatial dimensions, increasing the model's global perception capabilities. This attention mechanism does not reduce the model's computational efficiency, maintaining the real-time nature of the model's calculations. This improvement aims to enhance the perception system's ability to detect neighboring targets in ambiguous and complex underwater environments.

[0074] Furthermore, after obtaining the neighboring robot's position coordinates on the image through target detection, the disparity of the left and right binocular views within the target detection frame is obtained. To improve the computational efficiency of the perception system, the present invention uses the ORB feature extraction and matching method, which has the greatest advantage of rapid computational speed. After obtaining the left and right disparity, the three-dimensional relative distance and orientation information of the neighboring underwater robot is calculated based on the principle of binocular ranging.

[0075] Finally, the method was deployed on an underwater bionic robot prototype for experimental verification, verifying the method's real-time computing efficiency, target detection accuracy of neighboring robots, distance measurement accuracy, and orientation measurement accuracy to meet the requirements of cluster formation control. Figure 6 The underwater robot's perception of its neighbors at different distances is shown.

[0076] In one embodiment, using local perception technology, robot i adjusts its movement direction to maintain the desired triangle formation based on its relative positions to neighbors j and k. If the relative positions of adjacent robots deviate, the robot calculates the offset and adjusts its position using virtual forces.

[0077] This model, based on a virtual force control model and a local perception information model, establishes a formation motion model for underwater robot swarms. This model enables each robot to dynamically adjust its motion direction based on its surroundings, thereby stably forming a desired formation cluster. During this adjustment process, the robots ensure that the distance and angle with their neighbors meet the desired values, ultimately achieving a stable formation.

[0078] In one embodiment, a simulation experiment was conducted on the established underwater robot swarm formation motion model. In this experiment, the number of underwater robots was set to N = 6, and each robot's local visual perception range was set to 4 meters. For neighboring robots that were out of visual range, the system removed them from the neighbor set and disregarded their local decisions. Using local visual perception technology, the robots were able to obtain the relative position, distance, and orientation of neighboring robots within their field of view. This information was used to calculate a virtual force model to control the movement of the robot swarm.

[0079] The simulation parameters of the experiment are:

[0080] Number of robots: N=6.

[0081] Visual perception range: The perception range of each underwater robot is 4 meters.

[0082] Simulation time: 120 seconds.

[0083] Initial position: The initial positions of all underwater robots are set randomly.

[0084] Neighbor detection: For neighbors within the visual range, the robot calculates their relative position, relative distance, and relative orientation based on the visual perception algorithm.

[0085] In the experiment, the motion states of all underwater robots were adjusted in real time based on the position and motion information of neighboring robots. The desired formation was set to an isosceles triangle. Based on the calculated virtual forces, the robots would execute corresponding motion control, ultimately forming the target cluster. The results of the self-organized motion position of the underwater robot cluster are shown in the figure below. Figure 1 shown.

[0086] The simulation results show that this method can effectively realize the movement of underwater robot clusters, and the robots successfully move towards the set cluster shape. Figure 1 Relative position and Figure 2 The simulation results of relative orientation show that when the robots move in a cluster, their heading will be dynamically adjusted according to the information of their neighbors within their sight range. Figure 2 As can be seen, the robots undergo a navigation adjustment at 10 seconds. The relative positions and orientations of the robots change over time, but as the simulation time increases, the robots' headings stabilize, and the swarm gradually settles into the desired formation shape.

[0087] Reference Figure 3 As shown in Figure 1, the heading change diagram of 6 underwater robots during cluster movement. According to the simulation results, the heading change of the robots during cluster movement has certain fluctuations, but eventually tends to a stable orientation. Figure 4 The figure below shows the heading error of a swarm of six underwater robots during motion. The standard deviation of the heading error is 1.8°. The heading error is primarily influenced by the accuracy of neighbor detection, the error in calculating the relative positions between robots, and the accuracy of identifying neighbors within the visual range. Although some error exists, it is acceptable within a certain range because the virtual force model effectively controls the relative positions of the robots. After a long period of motion, the robot cluster gradually stabilizes, the heading error decreases, and the desired cluster formation is ultimately achieved.

[0088] Simulation experiments validated the feasibility and effectiveness of a local-awareness-based underwater robot swarming motion method. By combining a local-awareness algorithm with a virtual force model, the underwater robots were able to autonomously adjust their motion based on the relative positions and orientations of their neighbors, thereby forming a stable swarm. Despite some positional errors, simulation results demonstrate that this method effectively achieves swarming motion and forms the desired swarming pattern, providing a theoretical basis for practical underwater robot swarming motion.

[0089] Step 2: Deployment planning for the open water underwater robot swarm formation movement experiment

[0090] (1) Experimental purpose: To study the clustering behavior and underwater motion performance of underwater robots, test the clustering motion ability of underwater robots in lake environments, and improve the control algorithm and performance evaluation of underwater robots.

[0091] (2) Experimental location: Select an outdoor lake, ensure water quality and consider light conditions, ensure the effect of local perception and be able to use drones for aerial photography, and the lake should be of moderate size and without potential sources of danger.

[0092] (3) Experimental preparation:

[0093] Personnel Arrangements: One project leader will coordinate overall personnel work allocation and equipment preparation for the bionic fish experiments, and conduct pre-experimental risk assessments to ensure the safety of both the experimenters and the bionic fish. Five bionic fish operators will be responsible for debugging and controlling the bionic fish on the shore. One drone operator will observe and record the progress of each bionic fish swarm experiment using a drone. One data recorder will record experimental data and corresponding experimental results after each bionic fish swarm experiment. Five safety officers will ensure the safety of on-site personnel and equipment, handle emergencies, and promptly recover equipment and provide timely rescue for personnel. Five equipment managers will be responsible for safety inspections on the shore before each bionic fish experiment, releasing the bionic fish into the lake, and recovering and inspecting the bionic fish after the experiment.

[0094] Equipment and Tools: 15 underwater bionic fish, equipped with the necessary control and sensing communication equipment. Control equipment includes a radio, antenna, and remote control for each bionic fish, along with the corresponding host computer program. Data recording equipment (drone, camera, notebook, etc.). Rescue equipment (life jackets, life buoys, kayaks, long sticks, long ropes, etc.).

[0095] On-site setup: Delineate the lake swimming test area and mark the test boundaries. Set up equipment placement points, ensuring stability to ensure the safety of the bionic fish equipment and prevent water from entering the electronic equipment. Arrange appropriate personnel to guard the warning area to prevent unauthorized personnel from approaching and creating risks.

[0096] (4) Implementation steps:

[0097] First, prior to the cluster lake trial, operators were assigned to check the status of all bionic fish and control equipment, calibrating the binocular vision system to ensure accurate target recognition in the underwater environment. Each bionic fish was inspected for airtightness, and the battery level of each device was checked to ensure effective control between the device and the bionic fish. The bionic fish's actuators were debugged in air to ensure proper underwater operation. After the air-based electrical adjustments, the fish were placed in water for basic swimming tests to confirm the proper activation of the binocular vision system.

[0098] Next, the bionic fish are arranged in order in the designated waters, the formation of the bionic fish is initialized, the starting position and desired formation of the bionic fish are planned, and the role of each bionic fish in the cluster is described, such as the pilot bionic fish and the follower bionic fish.

[0099] Next, the bionic fish control system was activated and preliminary debugging was performed. The sensor system was used to identify and track the target. The bionic fish movement cluster was controlled according to a predetermined plan, with cluster formations set up and appropriate layouts planned, such as vertical columns and triangles. The experiment tested various target motion conditions, including linear motion and accelerated motion.

[0100] Finally, after the swarm formation experiment is complete, all experimental equipment will be retrieved and their status checked. The drone will also be recovered to ensure the complete preservation of the experimental data.

[0101] (5) Data Analysis

[0102] After the experiment is completed, the formation completion degree is used as the evaluation index to calculate the formation completion degree of different numbers of underwater bionic robots to verify that the expected formation effect is achieved. Figure 7 The figure shows the open water test process of the open water underwater robot cluster established in this embodiment.

[0103] Step 3: Calculation of underwater robot formation completion

[0104] Reference Figure 8 The figure shows the calculation diagram of the cluster formation completion degree. In this embodiment, it is assumed that the theoretical position coordinates of the underwater robot on the plane are P i (x i ,y i ), the actual coordinate position of the cluster experiment drone is P i '(x i ',y i '), then the distance between the theoretical position and the actual position is Then calculate the individual completion degree g of the underwater robot i ,

[0105]

[0106] Finally, according to the individual completion degree g of the underwater robot i Calculate the formation completion degree G,

[0107]

[0108] Reference Figure 9 The results of a swarm formation experiment involving three and six underwater robots on a lake are shown. The calculations above show that the swarm formation completion rate for three robots is 91.7%, while the swarm formation completion rate for six robots is 85%.

[0109] Reference Figure 10 The results of a swarm formation experiment involving 15 underwater robots on a lake are shown. Based on the above calculations, the completion rate for the 15 robots forming a single "I" formation was 63.6%, while the completion rate for the 15 robots forming two "I" formations was 81.3%. The formation completion rates indicate that as the number of underwater robots increases, their ability to complete the intended formation task decreases, and their effectiveness in achieving the desired formation objectives declines.

[0110] The underwater robot swarm formation movement and experimental method described in the present invention was used to realize the swarm movement experiment of 15 underwater manta ray-like robots on a lake for the first time, verifying the feasibility of the swarm formation method adopted in this paper and providing certain technical support for large-scale swarm applications.

[0111] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention without departing from the principles and purpose of the present invention.

Claims

1. An underwater robot swarm formation movement and experimental method, characterized in that The specific steps are as follows: Establish an individual virtual force control model for an underwater robot cluster, set up a formation motion model for N underwater robots, and update the position of individual underwater robots by obtaining the direction and magnitude of the resultant force of the N underwater robots. The individual virtual force control model includes individual underwater robot repulsion and individual underwater robot attraction. When the distance between adjacent robots is less than the desired relative distance, the robots exert repulsion on each other, and the repulsion increases as the distance decreases to avoid robot collisions. When the distance between robots is greater than the desired distance, the robots exert attraction, attracting each other and moving toward the set desired position, ultimately maintaining a fixed spacing and stably forming a cluster. A local perception information model for an individual underwater robot is established. Based on a target detection model, an ORB feature extraction and matching method is used to obtain the three-dimensional relative distance and orientation information between the individual underwater robot and its neighboring underwater robots. The local perception information model includes a Yolox target detection model and a binocular distance and orientation estimation model. Multiple motion modal image data of the underwater robot are obtained as a sample data set through a binocular camera in the binocular distance and orientation estimation model. The sample data set is input into the Yolox target detection model, and the position coordinates of the neighboring underwater robot on the image are output. The binocular distance and orientation estimation model uses an ORB feature extraction and matching method to obtain the disparity of the binocular left and right views within the target detection frame on the image. Based on the binocular ranging principle, the obtained disparity is used to calculate the three-dimensional relative distance and orientation information to the neighboring underwater robot. Based on the virtual force control model and the local perception information model, the desired underwater robot cluster formation is obtained through adjustment; Conduct underwater robot swarm formation movement experiments in open water; Based on the experimental data collected, the underwater robot cluster formation completion degree is calculated to verify the underwater robot cluster formation effect; The calculation method of the underwater robot cluster formation completion degree is: Assume that the theoretical position coordinates of the underwater robot on the plane are , the actual coordinate position of the cluster experiment drone is , then the distance between the theoretical position and the actual position is ; Calculating the individual completion of underwater robots , Where R is the distance deviation threshold between the given theoretical position and actual position of the underwater robot; According to the individual completion degree of underwater robots Calculate the completion of the formed formation , 。 2. The underwater robot swarm formation movement and experimental method according to claim 1, characterized in that: The method for obtaining the resultant force of the N underwater robots is that an individual underwater robot obtains the first-order derivative of the distance to its neighbor robots, and then sums the derivatives of the distances to all neighbors to obtain the resultant forces with all neighbors.

3. The underwater robot swarm formation movement and experimental method according to claim 2, characterized in that: The position update rule of the individual underwater robot is: in, is the total number of underwater robots, d is the relative distance between adjacent underwater robots, is the expected relative distance, is the relative position of adjacent underwater robots; a is the variable defining the repulsive force, and b is the variable defining the attractive force.

4. The underwater robot swarm formation movement and experimental method according to claim 3, characterized in that: A coordinated attention mechanism is set in the backbone feature extraction network of the Yolox target detection model. The coordinated attention mechanism simultaneously captures the dependencies between data channels and in spatial dimensions, increases the global perception ability of the model, and maintains the real-time performance of the model calculation.

5. The underwater robot swarm formation movement and experimental method according to claim 1, characterized in that: The experimental method for underwater robot cluster formation movement in open water is as follows: Calibrate the binocular vision system of each underwater robot and check that each underwater robot is in normal condition; Arrange the underwater robots in sequence in the designated waters, initialize the underwater robot cluster formation, plan the starting position and desired formation of the underwater robot cluster, and mark the pilot robot and follower robot; Start the underwater robot control system, conduct preliminary debugging, and use the perception system to identify and track the target; control the underwater robot cluster movement according to the predetermined plan, set the cluster formation, and plan a reasonable formation layout; After collecting data on various motion conditions of the test targets, the cluster formation experiment was completed, and all experimental equipment was recovered and its status checked.

6. An underwater robot swarm formation, characterized by: The invention comprises N underwater robots constituting a formation, namely, virtual force control models and local perception information models carried thereon, and controls the relative positions between adjacent underwater robots through the virtual force control model, thereby completing the motion control of the cluster formation; obtains the relative distance and orientation information of adjacent underwater robots through the local perception information model; further comprises at least one processor, and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute the underwater robot cluster formation motion and experimental method according to any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the underwater robot cluster formation movement and experimental method according to any one of claims 1 to 5 when executed.

Images