Distributed path planning method for multiple unmanned ships to pass through narrow water area

Through distributed optimization algorithms and multimodal network architecture, the communication safety and efficiency problems of multiple unmanned boats when sailing in narrow waters are solved, efficient and safe navigation among unmanned boats is achieved, and the intelligence of marine transportation is improved. and security.

CN118915729APending Publication Date: 2024-11-08DALIAN MARITIME UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410952595.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The prior art has failed to effectively solve the problems of communication safety, safe passage and efficiency when multiple unmanned boats sail in narrow waters, especially in complex sea conditions, resulting in unstable navigation and inefficiency.

Method used

Using distributed optimization algorithms and multimodal network architecture, local cost function and kinematic model are designed, real-time communication and path planning between unmanned boats are realized through multimodal networks, and potential functions are used to ensure the safe distance between unmanned boats and Efficient navigation.

Benefits of technology

It has achieved efficient coordination, security guarantee and path optimization of multiple unmanned boats in narrow waters, improved the stability and efficiency of the unmanned boat system, and ensured the stability and navigation safety of the unmanned boat formation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915729A_ABST
    Figure CN118915729A_ABST
Patent Text Reader

Abstract

The invention provides a distributed path planning method for multiple unmanned ships to pass through a narrow water area, and the method comprises the steps: designing a local cost function for the unmanned ships, and converting a path planning problem into a problem of solving a minimum value of the cost function; a kinematic model is designed for the unmanned ship, and then the problem of solving the minimum value of the cost function is converted into the design problem of unmanned ship input; designing a multi-modal network architecture, and designing control input for the unmanned ship; on the basis of a distributed optimization algorithm under a multi-modal network architecture, path planning is carried out on a multi-unmanned ship system, so that the unmanned ships can select different cost functions and parameters to safely and efficiently pass through according to terrains of different narrow water areas. The problem that the multiple unmanned ships pass through the narrow water area under the complex sea condition can be effectively solved, the efficiency of the multiple unmanned ships passing through the narrow water area is improved, and it is guaranteed that the multiple unmanned ship system can stably, efficiently and safely sail.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a distributed path planning method for multiple unmanned boats passing through narrow waters. Background Art

[0002] With the development of intelligent technology, unmanned boats are increasingly widely used in various fields. Unmanned boats have become an indispensable tool in the fields of marine scientific research, military, marine resource exploration, and maritime search and rescue. These unmanned boats can perform tasks in marine environments that are difficult for humans to reach or stay for a long time, improving operational efficiency and safety. The future development of the ocean urgently needs a large number of unmanned boats to support it. As a small surface platform with autonomous planning and autonomous navigation capabilities, unmanned boats can be used under extreme conditions or in places where personnel are difficult to carry out, which puts higher requirements on their own flexibility and motion trend forecasting in complex marine environments. Entering and exiting ports is one of the key technologies for realizing autonomous tasks of unmanned boats. Therefore, in order to smoothly execute the tasks of multiple unmanned boats, it is necessary to study the path planning of multiple unmanned boats entering and exiting ports. In order to ensure the safe and reliable communication between unmanned boats, the present invention proposes a polymorphic network architecture. In order to ensure the safe passage of unmanned boats in narrow waters, the present invention proposes an anti-collision algorithm. In order to solve the problem of the efficiency of multiple unmanned boats passing through narrow waters, the present invention proposes a distributed optimization algorithm to optimize the path.

[0003] In narrow waters, the coordinated navigation of multiple unmanned boats faces many technical difficulties. Although there have been some studies on the obstacle avoidance and navigation technology of unmanned boats, there is still a lack of in-depth research on the coordinated passage of multiple unmanned boats through narrow waters. Most of the previous studies focused on the path planning and obstacle avoidance technology of a single boat, but rarely paid attention to the coordination and communication issues of multiple boats in collaborative operation. Especially in terms of real-time communication, existing studies often ignore the complex interactive communication issues between multiple unmanned boats in narrow waters, which directly affect the maintenance of the formation and safe navigation of the unmanned boats; when the multiple unmanned boat system passes through narrow waters, the existing studies also fail to fully consider the efficiency of the multiple unmanned boat system. In view of this, the new collaborative navigation method through narrow waters actively responds to the technical development needs of intelligent marine transportation, and is committed to providing a comprehensive, safe and efficient method for multiple unmanned boats to pass through narrow waters. Through this method, we aim to achieve efficient coordination, safety assurance and path optimization of unmanned boats in narrow waters, and contribute to the improvement of intelligence and safety in the marine transportation industry. Summary of the invention

[0004] In view of this, the present invention provides a distributed path planning method for multiple unmanned boats passing through narrow waters. In order to ensure the safety and reliability of communication between unmanned boats, the present invention proposes a multimodal network architecture. In order to ensure the safe passage of unmanned boats in narrow waters, the present invention proposes an anti-collision algorithm. In order to solve the problem of the efficiency of multiple unmanned boats passing through narrow waters, the present invention proposes a distributed optimization algorithm to optimize the path. The present invention can effectively overcome the difficulty of multiple unmanned boats passing through narrow waters under complex sea conditions, improve the efficiency of multiple unmanned boats passing through narrow waters, and ensure that the multiple unmanned boat system can navigate stably, efficiently and safely.

[0005] To this end, the present invention adopts the following technical solutions:

[0006] The present invention provides a distributed path planning method for multiple unmanned boats passing through narrow waters, the steps comprising:

[0007] Design a local cost function for the unmanned boat and transform the path planning problem into a problem of solving the minimum value of the cost function;

[0008] Design a kinematic model for the unmanned boat, and then transform the problem of solving the minimum value of the cost function into a design problem of the input of the unmanned boat;

[0009] Design multimodal network architecture and control input for the unmanned boat;

[0010] Based on the distributed optimization algorithm under the multimodal network architecture, path planning is performed for the multi-unmanned boat system, so that the unmanned boats can select different cost functions and parameters to pass safely and efficiently according to the terrain of different narrow waters.

[0011] Furthermore, a local cost function is designed for the unmanned boat, including:

[0012] When the unmanned boats pass through narrow waters, each unmanned boat will find a suitable trajectory based on the standard route for narrow waters;

[0013] Use the spline interpolation method in mathematics to fit the trajectory of each unmanned boat, and use the obtained function as the local cost function f of the i-th unmanned boat i (η i (t),t): Its form is:

[0014]

[0015] in, represents the position of the i-th unmanned boat, represents the time-varying function of the i-th unmanned boat; the cost function represents the quantification of the actual position relative to the expected position.

[0016] Furthermore, a kinematic model is designed for the unmanned boat, including:

[0017] The unmanned boat motion model adopts a double integrator model:

[0018]

[0019] Among them, ν i (t) represents the speed of the i-th unmanned boat, τ i (t) represents the control input of the i-th unmanned boat.

[0020] Furthermore, a multimodal network architecture is designed, including:

[0021] The multimodal network consists of a data layer, a control layer and a service layer with fully-dimensionally definable functional planes. The data layer connects unmanned boats and ground stations to the network through a hybrid multimodal terminal identifier of a heterogeneous network, and provides them with a fully-dimensionally definable forwarding service; the control layer also incorporates IP identifiers, identity identifiers, content identifiers, and location identifiers into multimodal addressing and routing, adapts the service layer application to the network routing, and realizes control of the underlying data layer forwarding based on matching selection and on-demand switching mechanisms; the service layer realizes the optimization of the paths of multiple unmanned boat systems and collision avoidance services.

[0022] Furthermore, the control layer is functionally matched with four network modes: IP identification networking ensures the real-time reception and forwarding of the status information of the unmanned boat on the basis of the original communication function; location identification networking is used to transmit the geographical location information of the unmanned boat; identity identification networking is used to send communication requests of the unmanned boat and receive return results to assist the communication of the unmanned boat; content identification is used to transmit the video data collected by the unmanned boat to the ground station in real time.

[0023] Furthermore, the designed τ i (t) is:

[0024]

[0025] Among them, c1 and c2 are positive constants, sgn is a sign function, represents the potential function between the i-th and j-th unmanned boats.

[0026] Furthermore, the potential function is:

[0027]

[0028] Among them, d ij represents the expected distance between adjacent unmanned boats; potential function Yes | i -η j||2 non-negative differentiable function; b1, b2, b3, b4 and b5 are constants to ensure the potential function Continuous, and when ||η i / η j ||2=d ij When the minimum And d ij <Y.

[0029] Furthermore, when |η i (0)-η j (0)||2<Y, select As the potential function; otherwise, choose as a potential function.

[0030] The above technical solution has the following beneficial effects:

[0031] This invention is an innovative method proposed on the basis of in-depth research and analysis of cooperative navigation technology of unmanned boats. This method comprehensively considers the communication, path planning and obstacle avoidance technology among multiple boats, and establishes a control model for cooperative navigation of multiple boats while ensuring global navigation coordination and the safe operation constraints of each unmanned boat, so as to ensure the stability, safety and efficiency of the unmanned boat formation. Among them, this study designed a distributed optimization control method, which can effectively solve the influence of complex interactions among multiple boats on stable navigation in narrow waters, thereby ensuring the safe and efficient cooperative navigation of unmanned boats in narrow waters.

[0032] Through the real-time application of the present invention, the efficiency and safety of cooperative navigation of unmanned boats can be effectively improved, and the dependence on a single navigation system can be reduced, thereby promoting the development of intelligent ocean transportation. In a multi-boat navigation system, a distributed optimization control system under a multimodal network architecture is applied to achieve reliable communication between unmanned boats and complete distributed cooperative control decision calculations; at the same time, the distributed dynamic cooperative control method can better adapt to the distributed operation mode, handle complex interactions and uncertain information in narrow waters, and ensure the stability of the unmanned boat formation and the safety of navigation. Therefore, this research has important application value and social significance, and provides reliable technical support for the efficient cooperative navigation of unmanned boats in narrow waters. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0034] Figure 1A multi-unmanned boat communication architecture based on a multimodal network in an embodiment of the present invention;

[0035] Figure 2 It is Lingshui Port in the embodiment of the present invention;

[0036] Figure 3 It is a standard route in narrow waters in an embodiment of the present invention;

[0037] Figure 4 are the trajectory and speed of the unmanned boat under the conditions of Y=5, c1=5 and c2=1.5 in the embodiment of the present invention;

[0038] Figure 5 : is the trajectory and speed of the unmanned boat under the conditions of Y=10, c1=0.5 and c2=1 in the embodiment of the present invention;

[0039] Figure 6 ] are the trajectory and speed of the unmanned boat under the conditions of Y=30, c1=1 and c2=0.2 in the embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0041] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0042] The present invention provides a solution based on a distributed optimization algorithm and a multimodal network architecture to solve the problem of multiple unmanned boats passing through narrow waters safely and efficiently in a complex marine environment. The method is in line with the development trend of unmanned boats, promotes the development of the unmanned boat industry, and can effectively solve the problem of multiple unmanned boats passing through narrow waters. The present invention takes a multi-unmanned boat system as the research object, and establishes a distributed model of the multi-unmanned boat system based on the cost function, the communication between unmanned boats, and the safe and efficient navigation constraints of the unmanned boats. Based on distributed optimization and multimodal theory, the present invention proposes a distributed optimization processing method under a multimodal architecture, and the present invention proposes a potential function method for the safety problem between unmanned boats. The method effectively ensures that the unmanned boats pass through narrow waters safely, efficiently and without collision under the premise of safe and reliable communication.

[0043] The multimodal network architecture of the present invention is as follows Figure 1 As shown, the multimodal network consists of a data layer, a control layer and a service layer of a fully-dimensionally definable functional plane. The data layer connects the unmanned boat and the ground station to the network through a heterogeneous network multimodal terminal identifier, and the data layer provides a fully-dimensionally definable forwarding service. The control layer also incorporates IP identification, identity identification, content identification, and location identification into multimodal addressing and routing, adapts the service layer application to the network routing, and realizes the control of the underlying data layer forwarding according to matching selection and on-demand switching mechanisms. The service layer realizes the optimization and collision avoidance service of the multi-unmanned boat system path. The present invention takes the multi-unmanned boat system as the research object, designs the cost function based on the standard route method for narrow waters, and establishes a distributed model of the multi-unmanned boat system. Based on the network communication mode, the present invention proposes a multimodal network architecture that incorporates IP identification, identity identification, content identification and location identification into multimodal addressing and routing. Based on the distributed optimization theory, the present invention proposes a distributed optimization processing method under the multimodal architecture, and considers the situation where there may be collisions between unmanned boats, and designs a potential function method. Furthermore, the present invention can enable a multi-unmanned boat system to pass safely and efficiently by selecting different cost functions and parameters according to different narrow water scenarios based on stability proof.

[0044] This embodiment takes 5 unmanned boat systems as an example. Figure 2 In this embodiment, a distributed path planning method for multiple unmanned boats passing through narrow waters includes the following steps:

[0045] Step 1: Design a local cost function for the unmanned boat and transform the problem into a problem of solving the minimum value of the cost function; design a kinematic model for the unmanned boat and transform the problem into a design problem for the input of the unmanned boat.

[0046] When the unmanned boat passes through narrow waters, each unmanned boat will find a suitable trajectory according to the standard route in narrow waters. In this embodiment, the spline interpolation method in mathematics is used to fit the trajectory of each unmanned boat, and the obtained function is used as the local cost function of the i-th unmanned boat Its form is:

[0047]

[0048] in, represents the position of the i-th unmanned boat, Represents the time-varying function of the i-th unmanned boat. The cost function represents the quantification of the actual position relative to the desired position.

[0049] Then the global cost function f(η(t),t): It can be expressed as:

[0050]

[0051] According to the above relationship, it can be concluded that both the local cost function and the global cost function are convex functions. Therefore, there is an optimal state η * (t):

[0052] η * (t) = argminf(η(t), t);

[0053] η * (t) is the minimum value of the time-varying convex optimization problem.

[0054] Next, the kinematics of the USV are modeled.

[0055] The unmanned boat motion model adopts a double integrator model, as follows:

[0056]

[0057] Among them, ν i (t) represents the speed of the i-th unmanned boat, τ i (t) represents the control input of the i-th unmanned boat.

[0058] In a multi-UAV system, since there is no central control node and no data transmission to the central node is required, each UAV is considered as an autonomous entity. The goal is to design τ i (t), through the interaction of information with adjacent unmanned boats, local information is obtained to achieve the optimal state position η * (t). The above equation can be rewritten as:

[0059]

[0060] Ultimately, the goal is to solve the global cost function The minimization problem is to make the state position η of the i-th unmanned boat i (t) converges to the optimal path η * (t), thereby passing through narrow waters safely and efficiently.

[0061] At this point, step 1 of establishing the multi-unmanned boat system model is completed.

[0062] Step 2: Design a multimodal network architecture and design the control input τ for the unmanned boat i (t), through the stability proof, the unmanned boat can choose different cost functions and parameters to pass safely and efficiently according to the terrain of different narrow waters.

[0063] Firstly, a multimodal network architecture for multi-unmanned boat communication was established. The multimodal network consists of a data layer, a control layer, and a service layer with fully-dimensionally definable functional planes. The data layer connects the unmanned boat and the ground station to the network through a heterogeneous network multimodal terminal identifier, and the data layer provides a fully-dimensionally definable forwarding service. The control layer also incorporates IP identifiers, identity identifiers, content identifiers, and location identifiers into multimodal addressing and routing, adapts the service layer application to the network routing, and controls the forwarding of the underlying data layer according to matching selection and on-demand switching mechanisms. The service layer implements the optimization and collision avoidance services of the multi-unmanned boat system path. In this multimodal network architecture, the control layer matches the four network modes in terms of function: IP identifier networking ensures the real-time reception and forwarding of the unmanned boat status information based on the original communication function; location identifier networking is used to transmit the geographic location information of the unmanned boat; identity identifier networking is used to send the communication request of the unmanned boat and receive the return result to assist the communication of the unmanned boat; content identifier is used to transmit the video data collected by the unmanned boat to the ground station in real time.

[0064] Next, design the control input τ i (t):

[0065]

[0066] Among them, c1 and c2 are positive constants, sgn is a sign function, represents the potential function between the i-th and j-th unmanned boats.

[0067] In order to maintain connectivity between unmanned boats and prevent collisions, the following potential function is designed in this embodiment:

[0068]

[0069] Among them, d ij represents the expected distance between adjacent unmanned boats. Potential function Yes |i -η j ||2 is a non-negative differentiable function. b1, b2, b3, b4 and b5 are constants that ensure the potential function is continuous, and when ||η i / η j ||2=d ij It is worth noting that And d ij <Y.

[0070] then, The form is as follows:

[0071]

[0072] In order to maintain connectivity between unmanned boats. i (0)-η j (0)||2<Y, select As the potential function; otherwise, choose as a potential function.

[0073] At this point, step 2 is completed, which is the design of a distributed optimization algorithm under a multimodal architecture.

[0074] Step 3: Consider the actual port (Lingshui Port) and design a local cost function for each unmanned boat.

[0075] Five unmanned boats were selected for the experiment, and their local costs are shown below:

[0076]

[0077] At this point, the design of the cost function of the unmanned boat has been completed.

[0078] This embodiment aims at the problem of multiple unmanned boats safely and efficiently reaching Lingshui Harbor. Figure 4 is the trajectory and speed of the unmanned boat under the conditions of Y = 5, c1 = 5 and c2 = 1.5; Figure 5 is the trajectory and speed of the unmanned boat under the conditions of Y = 10, c1 = 0.5 and c2 = 1; Figure 6 The trajectory and speed of the unmanned boat under the conditions of Y = 30, c1 = 1 and c2 = 0.2. According to the above simulation diagram, it can be seen that the multi-unmanned boat path planning based on distributed optimization under the multimodal network architecture proposed in the present invention is effective.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distributed path planning method for multiple unmanned boats passing through narrow waters, characterized in that: The steps include: Design a local cost function for the unmanned boat and transform the path planning problem into a problem of solving the minimum value of the cost function; Design a kinematic model for the unmanned boat, and then transform the problem of solving the minimum value of the cost function into a design problem of the input of the unmanned boat; Design multimodal network architecture and control input for the unmanned boat; Based on the distributed optimization algorithm under the multimodal network architecture, path planning is performed for the multi-unmanned boat system, so that the unmanned boats can select different cost functions and parameters to pass safely and efficiently according to the terrain of different narrow waters.

2. A distributed path planning method for multiple unmanned boats passing through narrow waters according to claim 1, characterized in that: Design a local cost function for the unmanned boat, including: When the unmanned boats pass through narrow waters, each unmanned boat will find a suitable trajectory based on the standard route for narrow waters; Use the spline interpolation method in mathematics to fit the trajectory of each unmanned boat, and use the obtained function as the local cost function of the i-th unmanned boat Its form is: in, represents the position of the i-th unmanned boat, represents the time-varying function of the i-th unmanned boat; the cost function represents the quantification of the actual position relative to the expected position.

3. The distributed path planning method for multiple unmanned boats passing through narrow waters according to claim 1 is characterized in that: Design a kinematic model for the unmanned boat, including: The unmanned boat motion model adopts a double integrator model: Among them, ν i (t) represents the speed of the i-th unmanned boat, τ i (t) represents the control input of the i-th unmanned boat.

4. The distributed path planning method for multiple unmanned boats passing through narrow waters according to claim 1 is characterized in that: Design multimodal network architectures, including: The multimodal network consists of a data layer, a control layer and a service layer with fully-dimensionally definable functional planes. The data layer connects unmanned boats and ground stations to the network through a hybrid multimodal terminal identifier of a heterogeneous network, and provides them with a fully-dimensionally definable forwarding service; the control layer also incorporates IP identifiers, identity identifiers, content identifiers, and location identifiers into multimodal addressing and routing, adapts the service layer application to the network routing, and realizes control of the underlying data layer forwarding based on matching selection and on-demand switching mechanisms; the service layer realizes the optimization of the paths of multiple unmanned boat systems and collision avoidance services.

5. A distributed path planning method for multiple unmanned boats passing through narrow waters according to claim 4, characterized in that: The control layer matches the four network modes in terms of functions: IP identification networking ensures the real-time reception and forwarding of the status information of the unmanned boat based on the original communication function; The location identification network is used to transmit the geographical location information of the unmanned boat; The identity network is used to send communication requests to the unmanned boat and receive return results to assist the communication of the unmanned boat; The content identifier is used to transmit the video data collected by the unmanned boat to the ground station in real time.

6. A distributed path planning method for multiple unmanned boats passing through narrow waters according to claim 4 or 5, characterized in that: Designed Tau i (t) is: Among them, c1 and c2 are positive constants, sgn is a sign function, represents the potential function between the i-th and j-th unmanned boats.

7. A distributed path planning method for multiple unmanned boats passing through narrow waters according to claim 6, characterized in that: The potential function is: Among them, d ij represents the expected distance between adjacent unmanned boats; potential function is||η i -η j ||2 non-negative differentiable function; b1, b2, b3, b4 and b5 are constants to ensure the potential function Continuous, and when ||η i / η j ||2=d ij When the minimum And d ij <Y.

8. A distributed path planning method for multiple unmanned boats passing through narrow waters according to claim 7, characterized in that: When ||η i (0)-η j (0)||2<Y, select As the potential function; otherwise, choose as a potential function.