A multi-agent collaborative search path planning method based on temporal constraints

Abstract

The present application belongs to the technical field of task allocation, and specifically relates to a multi-agent collaborative search path planning method based on timing constraints. The method includes the following steps: initializing a set of agents and a set of target points to be searched; starting the first search phase, the global timer starts timing and performs an alternative target point search operation on all agents in turn; continuously sliding a time window forward as the global timer counts, and when the alternative target point of any agent enters the time window, performing a planned path update operation on the agent; re-execute the alternative target point search operation on all agents in turn until the set of target points to be searched is an empty set or the global timer reaches the end time of the first search phase. The present application selects the corresponding agent to perform the search task based on the time window, so as to avoid the situation where a certain agent falls into a local optimal search and causes low global search efficiency.

Description

Technical Field

[0001] The present application belongs to the field of task allocation technology, and specifically relates to a multi-agent collaborative search path planning method based on timing constraints. Background Art

[0002] With the rapid development of artificial intelligence and information technology, unmanned system technology is maturing, and its autonomous and reliable capabilities have significantly improved. Consequently, a relatively large number of research results have been generated in task allocation and path planning technologies among unmanned systems. In the military, unmanned systems can achieve not only intra-domain collaboration but also cross-domain collaboration across different domains (sea, land, and air). Unmanned system devices can establish collaborative mechanisms, achieving functional complementarity and increased energy efficiency through information sharing and integration, task coordination, and cooperation, thereby enabling unmanned systems within or across domains to perform coordinated combat missions. In the civilian sector, unmanned systems are becoming increasingly important in areas such as unmanned autonomous monitoring in the marine aquaculture industry, maritime meteorological monitoring operations, maritime search and rescue, and marine resource exploration and development. Current research on intra-domain and cross-domain collaboration among unmanned systems can be broadly categorized into collaborative trajectory planning, collaborative formation, and collaborative takeoff and landing, depending on the mission scenario.

[0003] In the area of ​​collaborative planning for unmanned systems, the current mainstream research directions are collaborative area coverage scanning technology and collaborative search path planning technology. The former focuses on situations where the target to be searched in the area is unknown, while the latter focuses on solving the problem of full coverage of known target points to be searched. Currently, in the technical field of collaborative search path planning, the main method is to allocate all the target points to be searched by assigning tasks one by one and cyclically to the agents within the unmanned system to achieve full coverage of the target points to be searched and collaborative planning between unmanned systems. Although this method can realize the rotation, one-by-one planning and allocation of agents, the search efficiency of different agents varies, both in the same domain and across domains. This makes collaborative planning not rationally planned according to the specific situation of the agents, reducing search efficiency and extending the total time of the global task. Summary of the Invention

[0004] The purpose of this application is to provide a multi-agent collaborative search path planning method that improves search efficiency and ensures the total time of the global task.

[0005] The embodiments of the present application can be implemented through the following technical solutions:

[0006] A multi-agent collaborative search path planning method based on time sequence constraints includes the following steps:

[0007] S100: Initializing an agent set and a target point set to be searched, wherein the agent set includes at least two agents, and the target point set to be searched includes at least two target points to be searched;

[0008] S200: Start the first search phase, the global timer starts timing and performs the candidate target point search operation on all agents in turn;

[0009] S300: Continuously sliding a time window forward as the global timer counts, and when the candidate target point of any agent enters the time window, performing a planned path update operation on the agent;

[0010] S400: re-execute the candidate target point search operation on all agents in sequence, and then return to execute step S300 until the set of target points to be searched is an empty set or the global timer reaches the end time of the first search phase.

[0011] Furthermore, for any agent, the candidate target point search operation includes:

[0012] Obtain the current location and estimated departure time of the agent, wherein the current location is the agent's mission starting location or the location of its most recently marked target point;

[0013] Based on the current position of the agent and under the constraints of the task constraints, the agent's alternative target point is determined by searching the target point optimization function, and the time when the agent arrives at its alternative target point is determined based on the expected departure time.

[0014] Furthermore, the planned path update operation includes the following steps:

[0015] C100: Determine whether any agent reaches its candidate target point within the time window. If so, execute steps C200 to C400. If not, delay the time step Δt and execute step C100 again.

[0016] C200: Mark the candidate target point as the determined target point of the agent, and extend the planned path of the agent from the last marked determined target point to the determined target point;

[0017] C300: taking the determined target point as the current position of the agent and updating the estimated departure time of the agent;

[0018] C400: Delete the determined target point from the set of target points to be searched.

[0019] Preferably, the intelligent agent includes at least one first type intelligent agent and at least one second type intelligent agent;

[0020] The search speed of the first type of intelligent agent is greater than the search speed of the second type of intelligent agent and the endurance time of the first type of intelligent agent is less than the endurance time of the second type of intelligent agent.

[0021] Furthermore, after step S400, the following steps are also included:

[0022] S500: Initiate the second search phase, re-execute the candidate target point search operation on all first-category agents in sequence, perform the parking operation on all second-category agents and obtain their position information;

[0023] S600: Continuously sliding a time window forward as the global timer counts, and when the candidate target point of any first-category agent enters the time window, performing a planned path update operation on the first-category agent;

[0024] S700: re-execute the alternative target point search operation for all first-category agents in sequence, and then return to execute step S600 until the set of target points to be searched is an empty set or the global timer reaches the end time of the second search phase.

[0025] Furthermore, the mission constraints include return time constraints;

[0026] When in the first search phase, the return time constraint condition is that the time it takes for the agent to return from its candidate target point to the mission starting position is less than its endurance time;

[0027] When in the second search phase, the return time constraint condition is that the movement time of the first type of intelligent agent from its candidate target point to the second type of intelligent agent closest to it is less than its endurance time.

[0028] Preferably, when the set of target points to be searched is not an empty set, the first search phase is terminated when at least one first-type agent fails to search and determine an alternative target point for the first time;

[0029] When the set of target points to be searched is not an empty set and all first-type agents are unable to search and determine the candidate target points, the second search phase is terminated.

[0030] Furthermore, step S700 further includes the following steps:

[0031] When any first-category intelligent agent is unable to search and determine an alternative target point when the target set to be searched is not an empty set, it moves to the second-category intelligent agent closest to it.

[0032] Furthermore, the task constraints also include the following constraints:

[0033] a. Each target point to be searched can only be marked as a confirmed target point of one agent;

[0034] b. The agent that needs to update global information during the search can communicate with other agents directly or indirectly via other agents;

[0035] c. Collision between agents is not allowed at any time.

[0036] Preferably, the candidate target point search operation is performed sequentially based on the search priority of each agent.

[0037] The embodiment of the present application provides a multi-agent collaborative search path planning method based on timing constraints, which has at least the following beneficial effects:

[0038] The embodiment of the present application provides a multi-agent collaborative search path planning method based on timing constraints, which selects the corresponding agent to perform the search task based on the time window, thereby avoiding the situation where a certain agent falls into the local optimal search and causes low global search efficiency;

[0039] In this application, based on the diversity of search tasks, a first-type intelligent agent and a second-type intelligent agent are set up to collaboratively complete the search task. Based on the performance difference between the intelligent agents, the search task is divided into a first search phase and a second search phase. The first-type intelligent agent performs the search task in both the first search phase and the second search phase. The second-type intelligent agent performs the search task in the first search phase and performs the task of picking up the first-type intelligent agent for return in the second search phase. This ensures that the first-type intelligent agent completes as many search tasks as possible within the flight time, improves the global search efficiency, and also ensures that the first-type intelligent agent can be led back by the second-type intelligent agent with sufficient flight time when the flight time is insufficient.

[0040] In this application, the termination of the first and second search phases is achieved by limiting the return time constraint, which takes into account the actual operation of the agent and enables the agent to complete the search task in different search phases with the greatest efficiency;

[0041] In this application, by setting the internal priority of the intelligent agent, the situation of competition and confusion caused by multiple intelligent agents being in the time window at the same time is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of the existing multi-agent collaborative search path planning method;

[0043] Figure 2 This is a flowchart of Example 1 of the multi-agent collaborative search path planning method based on timing constraints in this application;

[0044] Figure 3This is a schematic diagram of path planning for a specific embodiment at time T0;

[0045] Figure 4 A schematic diagram of path planning for a specific embodiment at time T1;

[0046] Figure 5 A line graph showing the change of target search coverage with α;

[0047] Figure 6 It is a line graph showing the change of target weight coverage with α;

[0048] Figure 7 A flowchart of the operation of performing the planned path update for the agent in this application;

[0049] Figure 8 This is a schematic diagram of path planning for a specific embodiment at time T2;

[0050] Figure 9 A schematic diagram of path planning for a specific embodiment at time T3;

[0051] Figure 10 This is a schematic diagram of path planning for a specific embodiment at time T4;

[0052] Figure 11 This is a schematic diagram of the process in which different target points are planned as search paths for different agents during the global timer sliding process from T0 to T4;

[0053] Figure 12 Schematic diagram of the multi-agent collaborative search path method in this application;

[0054] Figure 13 A schematic diagram showing a comparative analysis between the existing multi-agent collaborative search path planning method and the present application;

[0055] Figure 14 This is a flowchart of Example 2 of the multi-agent collaborative search path planning method based on timing constraints in this application;

[0056] Figure 15 This is a specific embodiment based on the simulation results of the multi-agent collaborative search path planning method in this application. DETAILED DESCRIPTION

[0057] Hereinafter, the present application will be further described based on preferred embodiments with reference to the accompanying drawings.

[0058] The terms used in this specification are intended to illustrate the embodiments of this application and are not intended to limit this application. Unless otherwise specified or limited, the terms "disposed," "connected," and "connected" should be understood broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections, direct connections, indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art will have a clear understanding of the specific meanings of the above terms in this application.

[0059] In addition, in the description of the embodiments of the present application, various components on the drawings are enlarged or reduced in size for ease of understanding, but this practice is not intended to limit the scope of protection of the present application.

[0060] Figure 1 This is an existing multi-agent collaborative search path planning method. The method assigns the search target points to each agent one by one and in sequence. Figure 1 Explain the method, Figure 1 The target points to be searched in the algorithm include target point 1, target point 2, target point 3, target point 4, and target point 5, and the agents include agent X and agent Y. The existing method will assign target point 1, target point 3, and target point 5 to agent X in sequence, and assign target point 2 and target point 4 to agent Y in sequence. The search time for agent X to complete target point 1 is 60 minutes, and the search time for agent Y to complete target point 2 is 20 minutes. The search time for agent X to complete target point 3 starting from target point 1 is 30 minutes, and the search time for agent Y to complete target point 4 starting from target point 2 is 30 minutes. The search time for agent X to complete target point 5 starting from target point 3 is 45 minutes. Figure 1 As shown in the figure, this method makes the total global task time 135 minutes ((60 minutes + 30 minutes + 45 minutes) > (20 minutes + 30 minutes)). That is, the task time of agent X is the sum of the task time of target points 1, 3, and 5, which is 135 minutes. The task time of agent Y is the task time of target points 2 and 4, which is 50 minutes.

[0061] by Figure 1 For example, we can see that during the last 10 minutes of Agent X's search for Target Point 1 and the entire search process for Target Points 3 and 5, Agent Y is idle. This greatly wastes Agent Y's search capability and efficiency during the entire search process. In addition, during the path planning process, the target points are simply allocated according to their order, without considering the impact of search time on the continuous operation of the agent. Therefore, this method has the problems of low search efficiency and long total global task time.

[0062] based on Figure 1 The problem of the multi-agent collaborative search path method in the present invention is that the present invention provides a multi-agent collaborative search path planning method based on timing constraints. The multi-agent collaborative search path planning method based on timing constraints in the present invention will be described in detail below. Figure 2 As shown, the method includes the following steps:

[0063] S100: Initializing an agent set and a target point set P to be searched, wherein the agent set includes at least two agents, and the target point set P to be searched includes at least two target points to be searched;

[0064] Where P = {P1, P2, ···, P Q}, Q is the maximum number of target points to be searched at the beginning of the search task, Q ≥ 2.

[0065] Specifically, Figure 3 Taking the steps of the search path planning method in the present application as an example, the agent set includes two agents, agent X and agent Y, and the target point set to be searched P = {P1, P2, P3, P4, P5}. The number of target points and agents set is the same as that of the prior art described above, to facilitate comparative analysis with the prior art.

[0066] In some preferred embodiments of the present application, the collaborative search path planning method can be applied to a large area where there are a large number of discretely distributed suspicious, dangerous, and other areas that require focused search. In view of the problem that the importance of target points in the large area varies, in order to ensure efficient search of different target points, in step S100, a weight set W of target points to be searched is also initialized. The weights of the weight set W of target points to be searched correspond one-to-one to the target points to be searched in the set P of target points to be searched, and the weight of each target point is set based on its importance.

[0067] Where W={W1,W2,···,W Q The weight value is between 1 and 10. The larger the value, the more important the target point to be searched is.

[0068] Specifically, Figure 3 For example, the weight set W of the target points to be searched includes weights W1, W2, W3, W4, and W5 corresponding to the target points to be searched P1, P2, P3, P4, and P5, which correspond to the importance of the target points to be searched.

[0069] S200: Start the first search phase, the global timer Timer starts timing and performs the candidate target point search operation on all agents in turn;

[0070] Furthermore, when the search task begins, the global timer Timer starts timing, and the clock frequency of each agent itself is synchronized with the global timer Timer to ensure the stability of operation and the efficiency of data processing.

[0071] Specifically, for any agent, the search operation for candidate target points includes:

[0072] Get the current location and estimated departure time of the agent, where the current location is the starting location of the agent's task or the location of its most recently marked target point.

[0073] Based on the current position of the agent, under the constraints of the task constraints, the agent's alternative target point is determined through target point optimization function search, and the time when the agent arrives at its alternative target point is determined based on the expected departure time.

[0074] by Figure 3 and Figure 4 For example, the five-pointed star in the figure represents the starting position of the task, the triangle represents the alternative target point, the circle represents the confirmed target point, and the square represents the target point to be searched in the set of target points to be searched that has not been determined as an alternative target point. That is, the points in the set of target points to be searched are the triangles and squares in the figure, the blue line represents agent X, and the red line represents agent Y. After the alternative target point is marked as a confirmed target point, the blue dotted line or red dotted line will become a blue solid line or a red solid line.

[0075] in, Figure 3 The figure shows the path planning diagram at the beginning of the search task (time T0). Based on the task constraints and the target point optimization function, Agent X and Agent Y respectively determine the target points P1 and P2 to be searched as candidate target points. At this time, the current positions of Agent X and Agent Y are the starting positions of the task, and the estimated departure time is when the global timer Timer reaches 0. Figure 4 The figure shows a schematic diagram of path planning during a search task (at time T1, where T1 > T0). P2 is marked as the determined target point. Based on P2, Agent Y searches and determines P3 as an alternative target point using task constraints and the target optimization function. At this point, Agent Y's current position is P2, and the estimated departure time is the time when Agent Y completes the search task at its current position (P2). Based on this estimated departure time and the distance between P2 and P3, Agent Y determines when it will arrive at the alternative target point P3. As can be seen from this specific embodiment, the alternative target point, determined target point, current position, estimated departure time, and target point to be searched are all variables and are not fixed at different times during the search process.

[0076] In some specific embodiments of the present application, the task constraints include the following constraints:

[0077] a. Each target point to be searched can only be marked as a confirmed target point of one agent;

[0078] b. Agents that need to update global information during the search can communicate with other agents directly or indirectly through other agents;

[0079] c. Collision between agents is not allowed at any time.

[0080] In some specific embodiments of the present application, the target optimization function is calculated using the following formula:

[0081]

[0082] Among them, α is an adjustable parameter with a value range of 0 to 1, which reflects the importance of time spent and the weight of the search target point in the search task. W is the time it takes for the agent to search from the current target point to the i-th target point to be searched, i is the weight corresponding to the search target point i, k is the kth agent, and C is the number of agents.

[0083] In some preferred embodiments of the present application, the value range of the adjustable parameter α is 0.5 to 0.9. Figure 5 and Figure 6 The target search coverage η for different numbers of target points to be searched is shown respectively P and target weight coverage η w The curve comparison chart with the change of adjustable parameter α shows that a larger target search coverage η can be obtained when the α value is 0.5-0.9 P and target weight coverage η w .

[0084] Among them, the target search coverage η P is the ratio of the number of searched targets to the total number of targets, and the target weight coverage η w It is the ratio of the sum of the weights of the searched targets to the sum of the weights of all targets, that is:

[0085]

[0086] Among them, X i Represents the target point P i Has it been searched? If it has been searched, then X i =1, otherwise X i =0.

[0087] S300: Continuously slide forward a time window T as the global timer Timer is counting wl, when the candidate target point of any agent enters the time window, that is, the time for any agent to reach its candidate target point is (Timer, Timer+T wl ) interval, perform the planned path update operation on the agent;

[0088] Specifically, if Figure 7 As shown, the planning path update operation includes the following steps:

[0089] C100: Determine whether any agent has reached its candidate target point and entered the time window. If so, execute steps C200 to C400. If not, delay the time step Δt and execute step C100 again.

[0090] C200: Mark the candidate target point as the determined target point of the agent, and extend the planned path of the agent from its last marked determined target point or the task starting position to the determined target point;

[0091] C300: The determined target point is used as the current position of the agent and the estimated departure time of the agent is updated. That is, the arrival time of the agent from the last marked determined target point or the task starting position to the determined target point is used as the estimated departure time of the agent from the current position (the determined target point).

[0092] C400: Delete the determined target point from the set P of target points to be searched.

[0093] by Figure 3 、 Figure 4 as well as Figure 11 For example, Figure 3 、 Figure 4 They are the path planning diagrams at different times. Figure 11 The figure shows a schematic diagram of the process in which different target points are planned as search paths for different agents during the sliding process of the global timer. Figure 11 The two moments T0 and T1 in Figure 3 、 Figure 4 Correspondingly, when the target point to be searched is a candidate target point, a dashed line connects it to the task starting position or the previously marked target point. When the candidate target point is marked as the corresponding agent's target point, the dashed line between it and the task starting position or the previously marked target point becomes a solid line, and the solid lines connecting them represent the corresponding agent's search path. In this embodiment, the initialized set of target points to be searched, P, = {P1, P2, P3, P4, P5}.

[0094] Specifically, see Figure 3 and Figure 11Explain the path planning at time T0 (when the search task starts). At the beginning of the search task, Agent X and Agent Y respectively determine P1 and P2 as candidate target points based on the task constraints and the target optimization function. As the time window slides, the time window moves to the right on the horizontal axis, as shown in the figure below. Figure 11 As shown, at time T1, the moment P2 of agent Y enters the time window, as shown in Figure 4 As shown, P2 is marked as the determined target point of agent Y from the alternative target point, and the planned path of agent Y extends from the starting position of the task (indicated by the letter O) to P2. The search path of agent Y is updated to O-P2, and the current position of agent Y becomes P2. The time when the search for P2 is completed is used as the estimated departure time from P2. P2 is deleted from the set of target points to be searched P, and the set of target points to be searched P becomes {P1, P3, P4, P5}. If the time of P1 of agent X does not enter the time window, the time window is extended by the time step Δt until it reaches time T2.

[0095] In some preferred embodiments of the present application, to prevent multiple agents from competing and causing confusion in the time sliding window, it is necessary to determine the internal priorities of the multiple agents before the search task begins to ensure the efficient and orderly search task. Furthermore, the search operation for candidate target points is performed sequentially based on the priority of each agent.

[0096] In some specific embodiments of the present application, the time window T wl The width of the time window T is no greater than the delay time step Δt, and the time window T wl The length of is small, which avoids the situation where two candidate target points of an agent appear at the same time in the same time window. And based on priority considerations, if the time window t wl If the width is greater than the delay time step Δt, it may cause the high-priority agent to appear in the time sliding window several times in a row, thereby causing the low-priority agent to lose the opportunity to select the target point to be searched.

[0097] In some preferred embodiments of the present application, when there is a weight set W of target points to be searched, the weight corresponding to the determined target point needs to be deleted from the weight set W of target points to be searched.

[0098] S400: re-execute the alternative target point search operation for all agents in sequence, and then return to step S300, until the set of target points to be searched P is an empty set or the global timer Timer reaches the end time of the first search phase.

[0099] Among them, if the set of target points to be searched P is an empty set, it means that all the target points to be searched have been searched.

[0100] The following will be combined Figure 3 、 Figure 4 、 Figures 8-11 Explain the cyclic execution process of this step and step S300. Figure 11 At different moments in Figure 3 、 Figure 4 、 Figure 8 、 Figure 9 、 Figure 10 Corresponding. Figure 4 and Figure 11 As shown in Figure 1, at time T1, after P2 is deleted from the set of target points to be searched P, based on the current position P2 and the expected departure time of agent Y, and through the task constraints and the target optimization function, P3 is determined as the candidate target point of agent Y from the set of target points to be searched {P1, P3, P4, P5}, and the expected arrival time at P3 is calculated; as shown in Figure 1 Figure 8 and Figure 11 As shown, at time T2, when the moment of P1 of agent X and P3 of agent Y enter the time window at the same time, P1 is marked from the candidate target point to the determined target point of agent X, and the planned path of agent X extends from the task starting position to P1. The search path of agent X is updated to O-P1, and the current position of agent X becomes P1. P3 is marked from the candidate target point to the determined target point of agent Y. The planned path of agent Y extends from the last marked determined target point P2 to P3, and the search path of agent Y is updated. The new position is O-P2-P3, the current position of agent Y becomes P3, and the search time of P1 and P3 is used as the estimated departure time from P1 and P3 respectively. P1 and P3 are deleted from the set of target points to be searched P. Based on the current position and estimated departure time of agents X and Y, and through the task constraints and the target optimization function, P5 and P4 are determined as the alternative target points of agents X and Y from the set of target points to be searched {P4, P5}, and the estimated arrival time to P5 and P4 is calculated; Figure 9 and Figure 11 As shown, at time T3, the specific execution process will not be described in detail. You can refer to the execution process at times T0, T1, and T2. The result at this time is that P4 is marked as the determined target point of agent Y, and the search path of agent Y is updated to O-P2-P3-P4, and the set of target points to be searched P becomes {P5}; at time T4, the result at this time is that P5 is marked as the determined target point of agent X, and the search path of agent X is updated to O-P1-P5, and the set of target points to be searched P becomes an empty set. It can be seen from this that Figure 11 The specific embodiment is a case where all target points to be searched have been searched and the first search phase is terminated.

[0101] In some preferred embodiments of the present application, there are objective facts that there are many target points to be searched and the search situation is complex, and multiple intelligent agents need to act on a search task at the same time. There must be performance differences between the multiple intelligent agents. The following considerations are based on the endurance time and search speed between different types of intelligent agents to achieve coordinated cooperation between different types of intelligent agents.

[0102] Specifically, the agents include at least one first-class agent and at least one second-class agent. The first-class agent's search speed is faster than that of the second-class agent, and the first-class agent's flight time is shorter than that of the second-class agent. Based on the respective characteristics of the first-class and second-class agents, the search paths of each agent are collaboratively planned at different stages of the search task to maximize overall search efficiency.

[0103] Furthermore, in step S100, the first type of agent set A and the second type of agent set B are initialized based on the first type of agent and the second type of agent respectively. Wherein, the first type of agent set A={A1, A2, A3, ···, A M}, M is the number of the first type of agents, M≥1, the set of the second type of agents B={B1,B2,B3,···,B N}, N is the number of the second type of intelligent agents, N≥1. In some specific embodiments of the present application, the first type of intelligent agent is a drone, and the second type of intelligent agent is an unmanned boat.

[0104] Furthermore, since the first type of intelligent agent has a fast search speed but a short endurance, and the second type of intelligent agent has a long endurance but a slow search speed, it is necessary to ensure that the first type of intelligent agent performs the search task within the endurance and meets the task constraints, so as to increase the number and weight of the searched target points within the maximum endurance.

[0105] For this reason, the search mission also includes a second search phase. During the first search phase, the first and second agents have relatively sufficient flight time, and both perform the search mission. If the set of target points to be searched, P, becomes empty, meaning all the target points have been searched, then the search mission will only have the first search phase. If the set of target points to be searched, P, is not empty, meaning not all the target points have been searched, the first search phase ends when at least one first-class agent is unable to identify an alternative target point for the first time, and the first and second agents enter the second search phase.

[0106] Further, if Figure 14 As shown, after step S400, the following steps are also included:

[0107] S500: Initiate the second search phase, re-execute the candidate target point search operation on all first-category agents in sequence, perform the parking operation on all second-category agents and obtain their position information;

[0108] That is, the search mission in this embodiment also includes a second search phase, which is initiated after the first search phase ends. During this second search phase, the first-class agent continues to perform the search mission within its maximum flight time, while the second-class agent docks at the last target point determined in the first search phase, awaiting the return of the first-class agent. The search for the candidate target point here is essentially the same as the one described above, differing only in that the target of this search is the first-class agent.

[0109] S600: Continuously slide forward a time window T as the global timer Timer counts wl , when the candidate target point of any first-class agent enters the time window, that is, the time for any first-class agent to reach its candidate target point is (Timer, Timer+T wl ) interval, the planning path update operation is performed on the first type of intelligent agent; the planning path update operation here is basically the same as the planning path update operation in the previous article, the only difference is that the object of the planning path update operation here is the first type of intelligent agent.

[0110] S700: Re-execute the alternative target point search operation for all first-category agents in sequence, and then return to execute step S600 until the set of target points to be searched P is an empty set or the global timer Timer reaches the end time of the second search phase.

[0111] The following describes a situation where the global timer Timer reaches the end time of the first search phase and the search task is completed.

[0112] In some preferred embodiments of the present application, during the execution of the search task, the return time of the intelligent agent must also be considered, and the return time is considered as a constraint condition of the first search stage to ensure that the intelligent agent can return smoothly while performing the search task.

[0113] Specifically, the task constraints also include a return time constraint. When the search task is in the first search phase, the return constraint is that the time it takes for the first type of agent to return from its alternative target point to the task starting position is less than its endurance time, that is, it must ensure that it can smoothly return to the task starting position after completing the alternative target point. The return position of all agents in this application is the task starting position. In actual applications, the return position can be set based on actual needs, and whether the return constraint conditions are met can be evaluated based on the specific return position.

[0114] Furthermore, when the set of target points to be searched P is not an empty set, the first search phase terminates when at least one first-category agent fails to search and determine an alternative target point for the first time. That is, when the search for all target points has not been completed, at least one first-category agent fails to meet the return time constraint and / or the above-mentioned constraints a, b, and c, making the agent unable to continue the search task and unable to determine an alternative target point for the search. At this time, the first search phase terminates. Specifically, taking 9 as an example, Figure 9 In the example, agent X takes 35 minutes to travel from P1 to P5. Assuming agent Y can return normally after completing the search for P4, agent X takes 80 minutes to return to the mission starting point from P5. Agent X's flight time is 90 minutes. Clearly, 90 minutes < (35 minutes + 80 minutes), meaning agent X cannot return after completing the search for P5. Even though not all search targets have been completed, the first search phase is terminated. This application achieves termination of the first search phase through constraints, taking into account the actual operating conditions of the agents, allowing the agents to complete the search task in the first search phase with maximum efficiency.

[0115] Furthermore, during the second search phase, the return constraint must also be considered. The return time constraint requires that the time it takes for the first-class agent to travel from its candidate target point to the closest second-class agent is less than the flight time. This means that after completing its search for the candidate target point, the first-class agent must be able to land safely on the closest second-class agent. If the flight time of the first-class agent is insufficient to support its search for the candidate target point and its arrival at the nearest second-class agent, the first-class agent will not meet the return time constraint and will be unable to search for and locate the candidate target point. The first-class agent will then move to the closest second-class agent, complete its search, and land on the closest second-class agent to await return.

[0116] Furthermore, when the set of target points to be searched P is not an empty set, and all first-category agents are unable to search and determine alternative target points, the second search phase terminates. That is, when the search for all target points to be searched has not been completed, all first-category agents do not meet the return time constraint and / or the above-mentioned constraints a, b, and c, that is, all first-category agents do not meet the conditions for continuing to perform the search task and are unable to determine alternative target points for the search, at which point the second search phase terminates. The present application achieves the termination of the second search phase through the restriction of constraints, taking into account the actual operating conditions of the agents, so that the first-category agents can complete the search task in the second search phase with the greatest efficiency.

[0117] The following combination Figure 1 、 Figure 12 and- Figure 13The effects of this application are illustrated by taking the example of Agent X and Agent Y searching P1, P2, P3, P4, and P5. Figure 1 、 Figure 12 and Figure 13 As shown by Figure 1 、 Figure 12 and Figure 13 It can be seen that this application can save 40 minutes compared with the existing method. The effect of shortening the total time is more obvious in the case of a large range and many target points. The method in this application can significantly shorten the total time of the global task and significantly improve the search efficiency, thereby making the saving effect of the total time of the global task more significant when performing a large-scale search task, and the search efficiency will be greatly improved. In summary, this application sets a time sliding window so that the alternative target point that slides into the time window is used as the path to determine the target point and join the corresponding intelligent agent. Based on the time window, the corresponding intelligent agent is selected to perform the search task, avoiding the situation where a certain intelligent agent falls into the local optimal search and causes low global search efficiency, thereby improving the search efficiency and ensuring the total time of the global task. [Specific embodiment]

[0119] In some specific embodiments of the present application, in order to calculate the time involved in the above-mentioned target optimization function, it is necessary to obtain the following variables. The definitions of these variables are as follows:

[0120] Variable 1: The agent's actual navigation path d ij

[0121] The actual navigation path d of the agent ij For the agent to move from the target point P i To the target point P j The Euclidean distance between them is calculated by the following formula:

[0122]

[0123] Among them, x i 、x j The target point P i 、P j The horizontal axis, y i 、y j The target point P i 、P j The vertical coordinate of .

[0124] Variable 2: Steering angle θ ijp

[0125] Steering angle θ ijp For the agent to move from the target point P i Navigate to the target point P j Then sail to P pThe steering angle is calculated based on the cosine theorem using the following formula:

[0126]

[0127] in, From the target point P i To the target point P j The vector of From the target point P j To the target point P p vector, steering angle θ ijp The range is [0,π].

[0128] Variable 3: Search time T ijp

[0129] Search time T ij The agent determines the target point as P i From the target point P j Navigate to the target point P p The time spent is calculated based on formula (4) and formula (5) by the following formula:

[0130]

[0131] Among them, V and ω are the linear velocity of the agent when sailing in a straight line and the angular velocity when turning, respectively.

[0132] Variable 4: The total search time T of the kth agent a (k)

[0133] Current total search time T a (k) is calculated based on formula (6) by the following formula:

[0134]

[0135] Where C is the number of agents, Indicates whether the kth agent is from P j Sail to P p , in the planning path of the kth agent, if there is a j Sail to P p ,but otherwise, That is, when the candidate target point P p If the time window is not entered or the sum of the current search time and the return time is greater than the corresponding agent's endurance, When the alternative target point P p When the time window is entered or the sum of the current search time and the return time is less than the corresponding agent's endurance,

[0136] Variable 5: Return time T of the kth first-class agent r (k)

[0137] When the kth first-class agent returns, the specific return point position of the first-class agent is first calculated based on the position of the second-class agent that chooses to land, and then its return time T is calculated according to formula (6) r (k).

[0138] The calculation process of the return point position is as follows: Assume that the last target point position determined before the first type of intelligent agent returns is P A (x A ,y A ), the position of the second type of agent is P S (x S ,y S ), then the return point P L (x L ,y L ) is calculated as follows:

[0139]

[0140] Among them, V1 is the linear velocity of the first type of intelligent agent returning home, and V2 is the linear velocity of the second type of intelligent agent receiving the flight.

[0141] Furthermore, when the search task is in the second search phase, the first type of agent can continue to perform the search task only if the return time constraint is met, that is,

[0142]

[0143] Among them, T max (k) represents the maximum flight time of the kth first-class agent. That is, when the search mission is in the second search phase, if the first-class agent meets the return time constraint and the set of target points to be searched P is not empty, the first-class agent will continue to perform the search mission. Otherwise, it will return with the corresponding second-class agent.

[0144] Variable 6: Waiting and operation time T before the kth agent sets out o (k)

[0145] Before departure, both the first and second type agents need operators to perform pre-departure inspection and preparation operations. Assume that the operator's inspection and preparation operation time is T s , then the waiting and operation time before the kth agent sets out is T o (k) is:

[0146]

[0147] Variable 7: Total task time T for the kth agent c (k)

[0148] The total task time T of the kth agent c (k) is the waiting time and operation time before departure T o (k) The sum of the total search time and the return time. If the agent is a second-class agent, there is no return time, that is:

[0149]

[0150] Variable 8: Global task total time T

[0151] The global total task time T is the maximum total task time of all first-class agents, that is:

[0152] T=max{T c (1),T c (2),…,T c (M)} (13);

[0153] Figure 15 It is shown that in a specific embodiment, in order to verify the search efficiency of the multi-agent collaborative search path planning method based on timing constraints in this application, this embodiment is based on the search target point in a 30km*30km sea area. Experiments are conducted, 100 target points to be searched are randomly generated in the target sea area, and the collaborative search task is completed by two types of agents: unmanned aerial vehicles (UAVs) and unmanned boats (USVs). To simplify the problem, we ignore the process of UAVs taking off and reaching the specified navigation altitude, and focus on the collaborative search path planning process between UAVs and USVs. When determining the number of UAVs and USVs for collaborative search, it is necessary to consider factors such as the requirements of the task itself and the maximum search range that a single VSV and UAV can cover. After comprehensive consideration, we chose 3 USVs and three UAVs to form a collaborative search system in this experiment. The target optimization parameter α is set to 0.7, and the relevant parameter information of USVs and UAVs is shown in Table 1.

[0154] Table 1 USV and UAV status parameter information

[0155]

[0156] like Figure 15As shown, the multi-agent collaborative search path planning method in this application plans appropriate search paths for three USVs and three UAVs. After departing from the base, the UAVs fly in three different directions respectively. Based on the above variables 1-variable 8 and according to the optimization of formula (1), the optimal candidate target point is selected each time, and the candidate target point is transformed into the determined target point based on the time window and the planned path is updated. The UAV completes the search for most of the target points to be searched within the endurance time; due to the slow navigation speed of the USV, it can only search for a smaller number of target points to be searched. After the end of the first search phase, the position at which it is located can be conducive to picking up the UAV with insufficient endurance time to return. Compared with the VAV returning to the shore base, the USV's nearby pick-up greatly reduces the time spent on the VAV's return journey, thereby improving the overall search efficiency.

[0157] The above is a detailed introduction to the specific implementation methods of the present application. For those skilled in the art, several improvements and modifications can be made to the present application without departing from the principles of the present application. These improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. A multi-agent collaborative search path planning method based on time constraints, characterized by: The following steps are involved: S100: Initializing an agent set and a target point set to be searched, wherein the agent set includes at least two agents, and the target point set to be searched includes at least two target points to be searched; The intelligent agents include at least one first-type intelligent agent and at least one second-type intelligent agent, wherein the search speed of the first-type intelligent agent is greater than the search speed of the second-type intelligent agent and the endurance of the first-type intelligent agent is less than the endurance of the second-type intelligent agent; S200: Start the first search phase, the global timer starts timing and performs the candidate target point search operation on all agents in turn; S300: Continuously sliding a time window forward as the global timer counts, and when the candidate target point of any agent enters the time window, performing a planned path update operation on the agent; S400: re-execute the candidate target point search operation on all agents in sequence, and then return to step S300 until the set of target points to be searched is empty or the global timer reaches the end time of the first search phase; After step S400, the following steps are also included: S500: Initiate the second search phase, re-execute the candidate target point search operation on all first-category agents in sequence, perform the parking operation on all second-category agents and obtain their position information; S600: Continuously sliding a time window forward as the global timer counts, and when the candidate target point of any first-category agent enters the time window, performing a planned path update operation on the first-category agent; S700: re-execute the alternative target point search operation for all first-category agents in sequence, and then return to execute step S600 until the set of target points to be searched is an empty set or the global timer reaches the end time of the second search phase.

2. The multi-agent collaborative search path planning method based on timing constraints according to claim 1 is characterized in that: For any agent, the candidate target point search operation includes: Obtain the current location and estimated departure time of the agent, wherein the current location is the agent's mission starting location or the location of its most recently marked target point; Based on the current position of the agent and under the constraints of the task constraints, the agent's alternative target point is determined by searching the target point optimization function, and the time when the agent arrives at its alternative target point is determined based on the expected departure time.

3. The multi-agent collaborative search path planning method based on timing constraints according to claim 2 is characterized in that: The planned path update operation includes the following steps: C100: Determine whether any agent reaches its candidate target point within the time window. If so, execute steps C200 to C400. If not, delay the time step Δt and execute step C100 again. C200: Mark the candidate target point as the determined target point of the agent, and extend the planned path of the agent from its last marked determined target point or the task starting position to the determined target point; C300: taking the determined target point as the current position of the agent and updating the estimated departure time of the agent; C400: Delete the determined target point from the set of target points to be searched.

4. The multi-agent collaborative search path planning method based on timing constraints according to claim 3 is characterized in that: The mission constraints include return time constraints; When in the first search phase, the return time constraint condition is that the time it takes for the agent to return from its candidate target point to the mission starting position is less than its endurance time; When in the second search phase, the return time constraint condition is that the movement time of the first type of intelligent agent from its candidate target point to the second type of intelligent agent closest to it is less than its endurance time.

5. The multi-agent collaborative search path planning method based on timing constraints according to claim 4 is characterized in that: When the set of target points to be searched is not an empty set, the first search phase terminates when at least one first-type agent fails to search and determine an alternative target point for the first time; When the set of target points to be searched is not an empty set and all first-type agents are unable to search and determine the candidate target points, the second search phase is terminated.

6. The multi-agent collaborative search path planning method based on timing constraints according to claim 4 is characterized in that: Step S700 also includes the following steps: When any first-category intelligent agent is unable to search and determine an alternative target point when the set of target points to be searched is not an empty set, it moves to the second-category intelligent agent closest to it.

7. The multi-agent collaborative search path planning method based on timing constraints according to claim 4 is characterized in that: The task constraints also include the following constraints: a. Each target point to be searched can only be marked as a confirmed target point of one agent; b. The agent that needs to update global information during the search can communicate with other agents directly or indirectly via other agents; c. Collision between agents is not allowed at any time.

8. The multi-agent collaborative search path planning method based on timing constraints according to claim 1 is characterized in that: The candidate target point search operation is performed sequentially based on the search priority of each agent.

Images