A method and system for intelligent assisted driving of ships in complex inland waterways

Abstract

This invention relates to an intelligent assisted driving method and system for vessels in complex inland waterways, comprising the following steps: Step S1: Acquiring water map information, AIS information, and on-site perception information, and fusing them after preprocessing to obtain navigation environment information; Step S2: Based on the navigation environment information, judging the vessel's navigation status and degree of danger through preset decision rules and algorithms, and outputting decision commands; Step S3: Based on the decision commands, planning a feasible trajectory using a path planning algorithm, and adjusting the trajectory according to real-time environmental changes; Step S4: Monitoring the deviation between the vessel's actual navigation status and the planned trajectory, adjusting the vessel's course and speed when the deviation exceeds a preset range, and simultaneously feeding back environmental changes to steps S2 and S3, re-deciding and replanning the path. This invention has the effects of rapid and accurate decision-making, dynamic planning of feasible trajectories, improved navigation safety and efficiency, and reduced operator workload.

Description

Technical Field

[0001] This invention relates to the field of intelligent ship driving technology, and in particular to an intelligent assisted driving method and system for ships in complex inland waterways. Background Technology

[0002] With the rapid development of inland waterway shipping, the number of ships continues to increase, and traffic flow in waterways near inland ports is becoming increasingly dense. Factors such as waterway restrictions, variable water flow, and complex obstacle distribution make the navigation environment for ships increasingly complex, placing higher demands on navigation safety and efficiency.

[0003] Currently, inland waterway navigation relies heavily on the experience and judgment of the operators. However, the rapidly changing environmental information in complex waters, the numerous surrounding vessels, and the vessel's own underactuated characteristics and high inertia make it difficult for operators to make quick and accurate avoidance decisions. Furthermore, the limited reaction time easily leads to safety accidents such as collisions and groundings. Existing ship navigation assistance systems can only provide limited information such as simple obstacle warnings and cannot integrate with water maps, etc. While comprehensive analysis of multi-source data, including on-site perception, is possible, there is a lack of dynamic adaptability to complex aquatic environments. It is difficult to plan and adjust feasible routes based on real-time conditions such as changes in water flow and ship motion. Furthermore, traditional driving methods cannot fully consider the impact of water flow on navigation, which can easily lead to the ship deviating from the planned route. Frequent turning and speed changes also place a great operational burden and decision-making pressure on the driver. Therefore, there is an urgent need for a ship intelligent assisted driving technology that can achieve rapid and accurate decision-making, dynamically plan feasible routes, and adapt to changes in complex environments to address the shortcomings of existing technologies. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide an intelligent assisted driving method and system for vessels in complex inland waterways, which has the effects of rapid and accurate decision-making, dynamic planning of feasible routes, improved navigation safety and efficiency, and reduced operator workload.

[0005] The above-mentioned objective of this invention is achieved through the following technical solutions: A method for intelligent assisted driving of vessels in complex inland waterways includes the following steps: Step S1: Obtain water map information information and on-site sensing information After preprocessing, the navigation environment information is fused together. Step S2: Based on the navigation environment information, determine the ship's navigation status and degree of danger through preset decision rules and algorithms, and output decision instructions; Step S3: Based on the decision instructions, a feasible path is planned using a path planning algorithm, and the path is adjusted according to real-time environmental changes; Step S4: Monitor the deviation between the ship's actual navigation status and the planned trajectory. When the deviation exceeds the preset range, adjust the ship's course and speed. At the same time, report the environmental changes to steps S2 and S3 to re-determine and replan the route.

[0006] Through the above technical solutions, a closed-loop assisted driving logic of "data fusion - real-time decision-making - path planning - deviation adjustment and feedback" is constructed. It can comprehensively integrate multi-source navigation information, accurately judge dangerous conditions, dynamically plan the optimal trajectory and correct deviations in real time, effectively improve the safety and efficiency of ship navigation in complex inland waterways, enhance adaptability to dynamic environments, and at the same time reduce the decision-making pressure and operational difficulty of the driver.

[0007] As a further technical solution of the present invention: step S1 includes: acquiring water map information. information and on-site sensing information ; Regarding the aforementioned water map information Unify data format and convert coordinate system for the above information and the on-site sensing information The Kalman filter algorithm is used for filtering. A weighted fusion algorithm is used to integrate the preprocessed water map information. information and on-site sensing information The fusion is performed using the following formula: ,in These are respectively water map information, The weights of information and on-site perceived information are dynamically adjusted based on data reliability and real-time performance. The fusion results are evaluated using mean squared error and consistency metrics, and the data fusion parameters and algorithms are adjusted based on the evaluation results.

[0008] The above technical solution first uses Kalman filtering to remove... The noise and measurement errors of the information and the on-site perception information are then integrated through a weighted fusion algorithm with dynamic weights to complete the integration of multi-source navigation environment data. At the same time, the mean square error and consistency index are used to evaluate the fusion effect and optimize the parameters, which effectively improves the accuracy and reliability of navigation environment information and provides high-quality data support for subsequent intelligent ship decision-making and dynamic path planning.

[0009] As a further technical solution of the present invention: step S2 includes: formulating decision rules, defining key variables based on ship kinematics and dynamics characteristics, channel conditions and the motion of surrounding ships, and calculating relative speed. and relative heading To determine the movement trend of the target vessel and the appropriate avoidance method; Introducing risk factor Assess the degree of danger and risk factor. The calculation formula is: ,in The maximum permissible speed of the vessel. To preset the risk factor threshold; Based on the decision rules and the risk assessment, a real-time decision-making algorithm is designed. The algorithm steps include sequentially calculating the relative velocity. and relative heading and risk factor ,when and If necessary, take directional or deceleration measures to avoid the obstacle; otherwise, maintain the current navigation status. Based on the decision result of the decision algorithm, decision instructions are output to the ship's control system.

[0010] The above technical solutions comprehensively cover key variables of ships and the environment, accurately judge the movement trend of target ships through relative speed and relative heading, and quantify the degree of risk by using a multi-factor weighted risk coefficient, making the output of decision-making instructions more targeted and scientific. They can output steering and speed adjustment instructions in a timely manner before the collision risk occurs, effectively reducing the incidence of ship collision accidents in complex inland waterways.

[0011] As a further technical solution of the present invention: step S3 includes: abstracting the complex inland waterway into a two-dimensional grid map. Taking into account waterway restrictions, obstacle distribution, water flow conditions, and node spacing, the edge cost of each navigation path is calculated. An improved A* algorithm is used for path planning, by evaluating the cost of each node. Choose the optimal path, where The actual cost of the path, The cost of heuristic estimation that integrates distance and angle factors; Real-time monitoring of changes in the aquatic environment; if new obstacles, changes in ship operation status, or changes in water flow are detected, the current course is locally optimized or global path planning is re-implemented based on the magnitude of the change.

[0012] The above technical solution abstracts complex inland waterways into a two-dimensional grid map containing multi-dimensional cost factors. Combined with the improved A* algorithm, it balances path cost and course matching degree, and supports dynamic path adjustment according to environmental changes. This achieves the optimality and flexibility of trajectory planning, ensuring that ships can maintain a safe and efficient navigation trajectory even under complex conditions such as waterway restrictions, obstacle distribution, and water flow changes.

[0013] As a further technical solution of the present invention: step S4 includes: calculating in real time the deviation between the actual course and the planned course of the ship. And the speed deviation between the actual speed and the planned speed. ; When the heading deviation or speed deviation When the preset threshold is exceeded, a PID controller is used to make closed-loop adjustments to the ship's course and speed respectively. Real-time monitoring of changes in water flow speed and direction, as well as changes in the position and course of surrounding vessels, and feedback of the monitored environmental change information to steps S2 and S3.

[0014] The above technical solution accurately calculates the deviation between course and speed and uses a PID controller for closed-loop adjustment. At the same time, it monitors environmental changes in real time and feeds them back to the decision-making and path planning stages. This not only ensures the stability of the ship's navigation status, but also enables rapid response to emergencies such as changes in water flow and ship turning, ensuring that the ship always follows the optimal course and improving the anti-interference capability of navigation.

[0015] As a further technical solution of the present invention: the method of using a PID controller to perform closed-loop adjustment of the ship's course and speed includes: According to the heading deviation The heading control quantity is calculated by the heading PID controller. According to the speed deviation The speed control quantity is calculated by the speed PID controller. ; in The calculation formulas are as follows: in, These are the proportional, integral, and derivative coefficients of the heading controller; These are the proportional coefficient, integral coefficient, and derivative coefficient of the speed controller.

[0016] Through the above technical solutions, dedicated PID control models are designed for heading and speed deviations, clarifying the roles of proportional, integral, and derivative coefficients. This makes the control quantity calculation more accurate and adaptable, enabling dynamic adjustment of the control strategy based on deviation characteristics. This achieves rapid and smooth correction of heading and speed, effectively reducing overshoot and adjustment time, and improving the stability and smoothness of ship navigation.

[0017] This invention also discloses an intelligent assisted driving system for vessels in complex inland waterways, comprising: The data acquisition module is used to acquire water map information, AIS information, and on-site perception information; The data fusion module is connected to the data acquisition module and is used to preprocess and fuse the acquired information to output navigation environment information. The real-time decision-making module is connected to the data fusion module and is used to determine the ship's navigation status and degree of danger based on navigation environment information, and output decision instructions. The dynamic path planning module is connected to the real-time decision-making module and is used to plan feasible routes based on decision instructions and dynamically adjust the routes according to environmental changes. The real-time control module is connected to the dynamic path planning module and the ship execution module respectively, and is used to monitor navigation deviations and adjust course and speed, while also feeding back environmental changes. The ship execution module is used to receive instructions from the real-time control module and perform heading and speed adjustment operations.

[0018] Through the above technical solution, each module has a clear division of labor and works in concert. The data acquisition module ensures comprehensive information sources, the data fusion module outputs accurate environmental information, the real-time decision-making module provides scientific instructions, the dynamic path planning module generates the optimal flight path, and the real-time control module and execution module ensure that the instructions are implemented. This realizes the systematic and automated implementation of intelligent assisted driving functions and improves the reliability and operating efficiency of the overall system.

[0019] The present invention also discloses an intelligent assisted driving device for vessels in complex inland waterways, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of an intelligent assisted driving method for vessels in complex inland waterways.

[0020] The above technical solutions deeply adapt intelligent assisted driving methods to ship-specific hardware equipment. Through the collaboration of memory, processor, dedicated sensors, and actuators, the stable and efficient execution of the method steps is ensured. This transforms intelligent assisted driving for ships in complex inland waterways from algorithm design into practically applicable hardware products, improving the operability and feasibility of the technical solutions.

[0021] The present invention also discloses a computer-readable storage medium storing an intelligent assisted driving program, wherein the intelligent assisted driving program, when executed by a processor, implements the steps of an intelligent assisted driving method for vessels in complex inland waterways.

[0022] The above technical solution stores the intelligent assisted driving algorithm in the form of a program on a computer-readable medium, realizing the portability and reusability of the algorithm, facilitating its deployment and application on different types of intelligent ship equipment, reducing the cost of technology promotion and implementation, and expanding the application scope of intelligent assisted driving methods for ships in complex inland waterways.

[0023] In summary, the present invention has at least one of the following beneficial technical effects: 1. This invention discloses an intelligent assisted driving method for vessels in complex inland waterways. Through a closed-loop design of "data fusion - real-time decision-making - dynamic path planning - deviation adjustment and feedback", it comprehensively integrates multi-source navigation information, accurately identifies dangerous states, dynamically optimizes the trajectory and corrects deviations in real time, effectively improving the safety and efficiency of vessel navigation in complex inland waterways and enhancing the adaptability to dynamic environments such as water flow changes and the appearance of obstacles.

[0024] 2. This invention discloses an intelligent assisted driving system for vessels in complex inland waterways. Through the coordinated linkage of data acquisition, fusion, decision-making, path planning, control, and execution modules, it realizes the systematic and automated implementation of intelligent assisted driving functions. Each module has a clear division of labor and smooth data transmission, ensuring the continuity and reliability of navigation environment perception, decision command output, and trajectory adjustment, and significantly reducing the decision-making pressure and operational difficulty of the driver. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating an intelligent assisted driving method for vessels in complex inland waterways according to the present invention.

[0026] Figure 2 for Figure 1 A flowchart illustrating the sub-steps of S1.

[0027] Figure 3 for Figure 1 A flowchart illustrating the sub-steps of S2.

[0028] Figure 4 for Figure 1 A flowchart illustrating the sub-steps of S3.

[0029] Figure 5 for Figure 1 A flowchart illustrating the sub-steps of S4. Detailed Implementation

[0030] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0031] In the description of this application, it should be noted that the terms "upper," "lower," "inner," "outer," "top / bottom," etc., indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0032] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installed," "equipped with," "sleeved / connected," "connected," etc., should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Example

[0033] Reference Figure 1 The present invention discloses an intelligent assisted driving method for vessels in complex inland waterways, comprising the following four steps: Step S1: Acquire maritime map information, AIS information, and on-site perception information, and fuse them after preprocessing to obtain navigation environment information; refer to Figure 2 Step S1 specifically includes the following sub-steps: S11, Data Acquisition In intelligent assisted driving systems for ships, information is obtained from water maps. AIS information and on-site sensing information Among them, the information on the water map. Obtained through the ship's navigation system, covering the width of inland waterways. , water depth Basic attributes such as obstacle distribution are relatively stable, but the update frequency is relatively low.

[0034] AIS Information The AIS receiver can receive the real-time positions of surrounding vessels. ,speed ,course Dynamic information; AIS information updates quickly and can reflect the real-time status of surrounding vessels, but signal loss or errors may occur. On-site sensing information. Collected by sensors such as radar and cameras installed on the ship, it mainly provides real-time obstacle information around the ship, such as the distance to obstacles. ,angle Etc. On-site sensing information has high real-time performance and accuracy, but the detection range and accuracy of sensors are greatly affected by environmental factors.

[0035] S12, Data Preprocessing Before data fusion, data from different sources needs to be preprocessed to eliminate noise and errors.

[0036] For information on water maps The main tasks are to unify the data format and convert the coordinate system to ensure that it is processed in the same coordinate system as other data.

[0037] For AIS information and on-site sensing information The Kalman filter algorithm is used for filtering.

[0038] Taking location data in AIS information as an example, let's assume... For the first The ship's actual position at all times. To predict the location, The observation location is given. The steps of the Kalman filter algorithm are as follows: Prediction steps: State prediction equation: ,in, Here is the state transition matrix. To control the input matrix, To control the input vector.

[0039] Covariance prediction equation: ,in, To predict the covariance matrix, Let be the process noise covariance matrix.

[0040] Update steps: Kalman gain calculation: ,in, For the observation matrix, To observe the noise covariance matrix.

[0041] State update equation: .

[0042] Covariance update equation: Kalman filtering can effectively reduce noise and errors in AIS and field perception information, thereby improving data accuracy.

[0043] S13, Data Fusion Algorithm The preprocessed water map information is processed using a weighted fusion method. and on-site sensing information The information is merged, and the merged information is denoted as . Then we have: in, The weights for the water map information, AIS information, and on-site perception information are respectively, and satisfy the following conditions: .

[0044] The weights are dynamically adjusted based on the reliability and real-time nature of the data. For example, during ship navigation, if the surrounding environment changes rapidly and the reliability of the on-site perception information is high, then the weights are increased. The value; if the ship is in a relatively stable waterway and the reliability of the maritime map information is high, then increase. The value of .

[0045] S14. Evaluation of Fusion Results To evaluate the effectiveness of data fusion, mean squared error (MSE) and consistency index (CI) were used. Mean squared error reflects the degree of error between the fused result and the true value, and is calculated using the following formula: in, For the fusion result, For the true value, The sample size is [number of samples]. The consistency index reflects the degree of consistency between different data sources, and is calculated using the following formula: in, For data from different data sources, This represents the number of data comparisons.

[0046] By evaluating the fusion results, the parameters and algorithms for data fusion are continuously adjusted to improve the accuracy and reliability of the fusion results.

[0047] Step S2: Based on the navigation environment information, determine the ship's navigation status and degree of danger using preset decision rules and algorithms, and output decision instructions; refer to Figure 3 Specifically, it includes the following sub-steps: S21. Formulating decision-making rules In the complex inland waterway navigation environment, vessel decision-making requires comprehensive consideration of multiple factors. Decision rules are formulated based on the vessel's kinematic and dynamic characteristics, channel conditions, and the motion of surrounding vessels. First, the following key variables are defined: The core of decision-making rules is to assess the ship's current navigational status and the level of danger it faces. When When this occurs, it indicates that the vessel is facing a collision hazard and needs to take evasive action. To determine the appropriate evasive action, relative speed is introduced. The calculation formula is as follows: Based on relative speed and relative heading, the movement trend of the target vessel relative to the ship can be further determined, thereby deciding whether to turn to avoid it or slow down and wait.

[0048] S22. Assess the level of risk To more accurately assess the level of danger faced by ships, a risk factor is introduced. The risk factor takes into account factors such as distance, relative speed, and relative heading. The calculation formula is as follows: in, These are the weighting coefficients, and It can be adjusted according to the actual navigation environment. This is the maximum permissible speed for the vessel.

[0049] when Exceeding a certain threshold At this point, it indicates that the vessel faces a high level of danger and requires immediate action. Threshold Determining the appropriate parameters requires combining extensive simulation experiments and actual navigation data to ensure that reasonable decisions can be made under different navigation environments.

[0050] S23, Design Decision Algorithm Based on the aforementioned decision-making rules and risk assessment, a real-time decision-making algorithm is designed. The algorithm's input is fused navigation environment information, including the speed, heading, and distance of the ship and surrounding target ships; the output is decision commands, such as turn left, turn right, or decelerate.

[0051] The specific algorithm steps are as follows: First, calculate the relative velocity. and relative heading ; Then calculate the risk factor. ; judge Is it true or false? If true, based on relative heading Based on the ship's turning ability, determine whether to turn left or right to avoid the obstacle; if turning to avoid the obstacle is not feasible, then decide to slow down and wait. If this is not the case, maintain the current navigation status.

[0052] S24, Output decision instructions The decision results are output to the ship's control system in the form of instructions. These instructions include steering angles. and speed adjustment amount The calculation of steering angle and speed adjustment needs to take into account the ship's maneuverability and actual navigation conditions. For example, when making a left turn to avoid an obstacle, the steering angle... According to relative heading and the ship's maximum turning angle Sure: Speed ​​adjustment amount Based on the risk factor and the ship's maximum deceleration capability Sure: The design of the above real-time decision-making module enables rapid and accurate decision-making in complex inland waterways based on real-time navigation environment information, thereby improving the safety and efficiency of ship navigation.

[0053] Step S3: Based on the decision instructions, a feasible path is planned using a path planning algorithm, and the path is adjusted according to real-time environmental changes; This module, based on real-time decision-making results, employs advanced path planning algorithms, comprehensively considering various factors in the complex inland waterways, to dynamically plan safe, feasible, and efficient routes, and can continuously adjust the route based on real-time information. (Refer to...) Figure 4 Specifically, it includes the following sub-steps: S31. Environmental Modeling: Constructing a Mesh Model of Complex Inland Waterways To accurately describe the complex aquatic environment of inland waterways, it is abstracted into a two-dimensional grid map. ,in For a set of grid nodes, This is the set of edges connecting nodes. Each node... Represents a specific location, the state of which is determined by coordinates. Representation. Edges between nodes. This represents the possible navigation paths of a ship, with each edge having a corresponding cost. The cost calculation takes into account a variety of factors.

[0054] Channel restrictions are one of the important factors; let the channel width be... ,node The distance to the channel boundary is The cost of waterway restrictions It can be represented as: in It is a very small positive number, used to avoid the denominator being zero.

[0055] The distribution of obstacles also affects the cost; let's define nodes. The distance to the nearest obstacle is Then the cost of the obstacle for: in This is the safe distance threshold.

[0056] The water flow situation is also not negligible; let the water flow velocity be... The speed of the ship relative to the water is The cost of water flow impact for: Taking all the above factors into account, Connecting nodes The cost for: in These are the weighting coefficients. For nodes The Euclidean distance between them.

[0057] S32. Path Planning: Execute the improved A* algorithm to search for the optimal path. An improved A* algorithm is used for path planning. The A* algorithm evaluates the cost of each node. To select the optimal path, where From the starting node to the node The actual cost, From node Heuristic cost estimation to the target node.

[0058] In this module, The calculation takes into account the cost of the edges, i.e. ,in From the starting node to the node The path.

[0059] To better adapt to the characteristics of complex inland waterways, a new heuristic function was designed. Considering the ship's maneuverability and the actual conditions of the waterway, the heuristic function integrates distance and angle factors. Let the target node be... ,node The straight-line distance to the target node is ,node The angle between the heading and the target direction is Then the heuristic function for: in These are the weighting coefficients.

[0060] The algorithm starts from the initial node and continuously expands to have the smallest The process continues until the target node is found or all reachable nodes have been traversed. When expanding a node, the validity of adjacent nodes is checked to ensure that it is within the path and away from obstacles.

[0061] S33, Route Adjustment: Monitor environmental changes and dynamically optimize the flight path. During ship navigation, environmental changes are monitored in real time. When new obstacles are detected, the motion of surrounding ships changes, or water flow conditions change, the cost of the relevant nodes is recalculated.

[0062] Suppose a new obstacle is detected at a certain moment, node The distance to the new obstacle becomes Then update the obstacle cost. And recalculate the cost of the affected edges. .

[0063] Based on the updated cost, the current path is adjusted locally or globally. If the change is minor, only the path in the affected area is locally optimized; if the change is significant, the A* algorithm is restarted for global path planning.

[0064] Through the above steps, the dynamic path planning module can plan a safe and efficient route based on the real-time conditions of complex inland waterways, and adjust the route in a timely manner to ensure the safety and efficiency of ship navigation.

[0065] Step S4: Monitor the deviation between the ship's actual navigation status and the planned trajectory. When the deviation exceeds a preset range, adjust the ship's course and speed, and simultaneously report environmental changes. This environmental change information is also fed back to steps S2 and S3 for re-decision and route planning. (Refer to...) Figure 5 Specifically, it includes the following sub-steps: S41. Navigation Status Monitoring and Deviation Calculation During ship navigation, various sensors installed on the ship (such as gyroscopes and speedometers) are used to obtain real-time information about the ship's actual navigation status. Let the ship's actual heading be... The actual speed is The expected heading at the corresponding location on the planned path is The expected speed is .

[0066] heading deviation It can be calculated using the following formula: Speed ​​deviation It can be calculated using the following formula: These deviation values ​​are important criteria for determining whether a ship has deviated from its planned path.

[0067] S42. Deviation-based control strategy When the heading deviates or speed deviation When the speed exceeds the preset allowable range, the ship's course and speed need to be adjusted.

[0068] For heading adjustments, a proportional-integral-derivative (PID) controller is used. The output of the PID controller... It can be represented as: in, This is the proportionality coefficient. The integral coefficient is... is the differential coefficient. A steering device used to control a ship, causing the ship's course to gradually approach the desired course.

[0069] For speed adjustment, a PID controller is also used. Its output... It can be represented as: in, This is the proportionality coefficient. The integral coefficient is... is the differential coefficient. The propulsion system used to control a ship, gradually bringing the ship's speed closer to the desired speed.

[0070] S43. Real-time feedback and processing of environmental changes In complex inland waterways, environmental factors such as changes in water flow speed and direction, and sudden turns by other vessels can affect ship navigation. Real-time monitoring of these environmental changes and feedback to the real-time decision-making module and dynamic path planning module are crucial.

[0071] Let the water flow velocity be , its in The directional components are respectively and The speed of the ship relative to the ground. It can be expressed as the speed of the ship relative to the water flow. With water flow velocity vector sum: When a change in water flow speed or direction is detected, the ship's actual navigation state is recalculated according to the above formula, and the deviation value is updated. Simultaneously, the water flow change information is transmitted to the dynamic path planning module, which replans the path to adapt to the new environment.

[0072] For sudden turns by other vessels, monitor their position and course changes in real time. Let the positions of the other vessels be denoted as . The heading is Calculate the relative positions of this vessel and other vessels. and relative heading When the relative position and relative heading meet certain dangerous conditions (such as the relative distance being less than the safe distance and the relative heading angle potentially leading to a collision), the information is promptly fed back to the real-time decision-making module for re-decision-making and path planning to avoid a collision.

[0073] The design of the above real-time adjustment module enables ships to adapt to environmental changes in complex inland waterways in real time, maintaining safe and efficient navigation on the planned route.

[0074] This invention also discloses an intelligent assisted driving system for vessels in complex inland waterways, comprising a data acquisition module, a data fusion module, a real-time decision-making module, a dynamic path planning module, a real-time control module, and a vessel execution module. The data acquisition module acquires water map information, AIS information, and on-site perception information. The data fusion module, connected to the data acquisition module, preprocesses and fuses the acquired information and outputs navigation environment information. The real-time decision-making module, connected to the data fusion module, determines the vessel's navigation status and risk level based on the navigation environment information and outputs decision commands. The dynamic path planning module, connected to the real-time decision-making module, plans feasible routes based on decision commands and dynamically adjusts the route according to environmental changes. The real-time control module, connected to both the dynamic path planning module and the vessel execution module, monitors navigation deviations and adjusts course and speed, while also providing feedback on environmental changes. The vessel execution module receives commands from the real-time control module and executes course and speed adjustment operations.

[0075] Furthermore, the present invention provides an intelligent assisted driving device for vessels in complex inland waterways, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the aforementioned intelligent assisted driving method. The present invention also provides a computer-readable storage medium storing an intelligent assisted driving program, which, when executed by a processor, implements the steps of the aforementioned intelligent assisted driving method for vessels in complex inland waterways.

[0076] The implementation principle of this invention is based on the collaborative operation of data fusion, real-time decision-making, path planning, and closed-loop control. The system first acquires surface map information, AIS information, and sensor-based on-site perception information via a data acquisition module. Subsequently, the data fusion module performs Kalman filtering on the AIS information and on-site perception information to reduce noise interference, and then uses a weighted fusion algorithm with dynamically adjustable weights. The preprocessed data from the two types of data are then fused with maritime map information to form unified, high-precision navigation environment information. During the fusion process, weights are... The system adaptively adjusts based on the reliability and real-time performance of each data source, while also utilizing mean square error. and consistency indicators The fusion results are quantitatively evaluated, and the fusion parameters are optimized in reverse to ensure information quality.

[0077] The real-time decision-making module receives the fused navigation environment information and first calculates the relative speed between the ship and the target ship. Relative heading and the distance between the two shipsd Then substitute the above parameters into the risk factor formula. Conduct a quantitative risk assessment. Once it is determined that the collision risk conditions are met... At that time, the module outputs avoidance decision instructions that include steering angle or speed adjustment.

[0078] Based on the aforementioned decision instructions, the dynamic path planning module first abstracts the complex inland waterway into a two-dimensional grid map to complete environmental modeling; the cost of each connecting edge in the map... c(e), The optimal path is calculated by comprehensively considering constraints such as channel limitations, obstacle distances, water flow effects, and Euclidean distances between nodes. An improved A* algorithm is used for optimal path search, and its heuristic function is... The straight-line distance from the innovative fusion node to the target node Angle with heading Right now , (As weight coefficients), enabling the planning of the initial optimal trajectory under complex constraints. During the ship's navigation, if environmental changes are detected (such as the addition of obstacles or sudden changes in water flow), the cost of the relevant edges is updated in real time, triggering local optimization or global replanning of the path.

[0079] The real-time control module continuously monitors the deviation between the ship's actual course and speed and the planned values. When the deviation exceeds the preset threshold, the independent PID controller is invoked to calculate and output the heading control quantity. and speed control quantity This module drives the ship's actuators to complete adjustments. Simultaneously, it feeds back real-time environmental changes, such as water flow variations and the dynamics of other vessels, to the real-time decision-making module and the dynamic path planning module, ultimately forming a dynamic closed-loop control system of "perception-decision-planning-execution-feedback".

[0080] Through the aforementioned modular collaborative and closed-loop management technology process, this invention can effectively improve the automation level and safety of ship navigation in complex inland waterways.

[0081] The embodiments described herein are preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape, and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A method for intelligent assisted driving of vessels in complex inland waterways, characterized in that, Includes the following steps: Step S1: Obtain water map information information and on-site sensing information After preprocessing, the navigation environment information is fused together. Step S2: Based on the navigation environment information, determine the ship's navigation status and degree of danger through preset decision rules and algorithms, and output decision instructions; Step S3: Based on the decision instructions, a feasible path is planned using a path planning algorithm, and the path is adjusted according to real-time environmental changes; Step S4: Monitor the deviation between the ship's actual navigation status and the planned trajectory. When the deviation exceeds the preset range, adjust the ship's course and speed. At the same time, report the environmental changes to steps S2 and S3 to re-determine and replan the route.

2. The intelligent assisted driving method for vessels in complex inland waterways according to claim 1, characterized in that, Step S1 includes: Obtain water map information information and on-site sensing information ; Regarding the aforementioned water map information Unify data format and convert coordinate system for the above information The on-site sensing information The Kalman filter algorithm is used for filtering. A weighted fusion algorithm is used to integrate the preprocessed water map information. information and on-site sensing information The fusion is performed using the following formula: ,That middle These are respectively water map information, The weights of information and on-site perceived information are dynamically adjusted based on data reliability and real-time performance. The fusion results are evaluated using mean squared error and consistency metrics, and the data fusion parameters and algorithms are adjusted based on the evaluation results.

3. The intelligent assisted driving method for vessels in complex inland waterways according to claim 1, characterized in that, Step S2 includes: Develop decision-making rules based on the ship's kinematics and dynamics, channel conditions, and the motion of surrounding vessels; define key variables; and calculate relative speeds. and relative heading To determine the movement trend of the target vessel and the appropriate avoidance method; Introducing risk factor Assess the degree of danger and risk factor. The calculation formula is: , The maximum permissible speed of the vessel. To preset the risk factor threshold; Based on the decision rules and the risk assessment, a real-time decision-making algorithm is designed. The algorithm steps include sequentially calculating the relative velocity. and relative heading and risk factor ,when If necessary, take directional or deceleration measures to avoid the obstacle; otherwise, maintain the current navigation status. Based on the decision result of the decision algorithm, decision instructions are output to the ship's control system.

4. The intelligent assisted driving method for vessels in complex inland waterways according to claim 1, characterized in that, Step S3 includes: Abstracting complex inland waterways into a two-dimensional grid map Taking into account waterway restrictions, obstacle distribution, water flow conditions, and node spacing, the edge cost of each navigation path is calculated. Adopting improved The algorithm performs path planning by evaluating the cost of each node. Choose the optimal path, where The actual cost of the path, The cost of heuristic estimation that integrates distance and angle factors; Real-time monitoring of changes in the aquatic environment; if new obstacles, changes in ship operation status, or changes in water flow are detected, the current course is locally optimized or global path planning is re-implemented based on the magnitude of the change.

5. The intelligent assisted driving method for vessels in complex inland waterways according to claim 1, characterized in that, Step S4 includes: Real-time calculation of the deviation between the ship's actual course and its planned course And the speed deviation between the actual speed and the planned speed. ; When the heading deviation or speed deviation When the preset threshold is exceeded, a PID controller is used to make closed-loop adjustments to the ship's course and speed respectively. Real-time monitoring of changes in water flow speed and direction, as well as changes in the position and course of surrounding vessels, and feedback of the monitored environmental change information to steps S2 and S3.

6. The intelligent assisted driving method for vessels in complex inland waterways according to claim 5, characterized in that, The method of using a PID controller to perform closed-loop adjustments to the ship's course and speed includes: adjusting the course deviation according to the deviation. The heading control quantity is calculated by the heading PID controller. According to the speed deviation The speed control quantity is calculated by the speed PID controller. ; in The calculation formulas are as follows: in, These are the proportional coefficient, integral coefficient, and derivative coefficient of the heading controller; These are the proportional coefficient, integral coefficient, and derivative coefficient of the speed controller.

7. An intelligent assisted driving system for vessels in complex inland waterways, characterized in that, include: The data acquisition module is used to acquire water map information, AIS information, and on-site perception information; The data fusion module is connected to the data acquisition module and is used to preprocess and fuse the acquired information to output navigation environment information. The real-time decision-making module is connected to the data fusion module and is used to determine the ship's navigation status and degree of danger based on navigation environment information, and output decision instructions. The dynamic path planning module is connected to the real-time decision-making module and is used to plan feasible routes based on decision instructions and dynamically adjust the routes according to environmental changes. The real-time control module is connected to the dynamic path planning module and the ship execution module respectively, and is used to monitor navigation deviations and adjust course and speed, while also feeding back environmental changes. The ship execution module is used to receive instructions from the real-time control module and perform heading and speed adjustment operations.

8. The intelligent assisted driving equipment for vessels in complex inland waterways according to claim 1, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium according to claim 1, characterized in that, The computer-readable storage medium stores an intelligent assisted driving program, which, when executed by a processor, implements the steps of the intelligent assisted driving method for vessels in complex inland waterways as described in any one of claims 1 to 6.

Images