Autonomous navigation system considering ship obstacle avoidance

Abstract

The invention discloses an autonomous navigation system considering ship obstacle avoidance. The autonomous navigation system comprises an environmental information collection module, a path planning module, a real-time information acquisition module, an environmental risk fusion module, a potential field setting module and an autonomous navigation module. According to the method, a risk identification and evaluation method and an artificial potential field method are effectively combined, information such as ship navigation information and environmental risk sensing wind wave flow is effectively utilized, and safe and efficient ship navigation and intelligent formation control are achieved.

Description

Technical Field

[0001] The present invention belongs to the field of information perception technology and ship formation control technology, and specifically relates to an autonomous navigation system taking ship obstacle avoidance into consideration. Background Art

[0002] Traditional ships need human intervention to navigate, which increases the risk of accidents caused by human error and negligence; therefore, an autonomous ship navigation technology is needed to follow an efficient path so that the ship can navigate autonomously without human intervention. When a ship is navigating autonomously, it needs to avoid collisions with obstacles in the ocean or river, so how to make the ship turn spontaneously and how to control the ship's route to autonomously adjust are challenging tasks. Summary of the invention

[0003] In view of the shortcomings of the existing technology, the present invention proposes an autonomous navigation system that takes ship obstacle avoidance into consideration. It effectively combines the risk identification and assessment method with the artificial potential field method, and effectively utilizes the ship navigation information and environmental risk perception wind, wave, current and other information to achieve safe and efficient navigation of ships and intelligent formation control.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] An autonomous navigation system considering ship obstacle avoidance, comprising: an environmental information collection module, a path planning module, a real-time information collection module, an environmental risk fusion module, a potential field setting module and an autonomous navigation module;

[0006] The environmental information collection module is used to collect ship navigation environment information and ship AIS data using ship navigation equipment;

[0007] The path planning module is used to conduct risk assessment on the information collected by the ship, set the starting point and end point of the ship's navigation, formulate a specific ship's navigation path plan, and obtain the planned route information;

[0008] The real-time information acquisition module is used to obtain real-time information of the ship formation by collecting information about the ship's own state and the external environment in real time during the motion control process of executing the planned route;

[0009] The environmental risk fusion module is used to fuse environmental risks using a fuzzy risk assessment method to obtain local environmental information;

[0010] The potential field setting module is used to establish a ship collision avoidance and obstacle avoidance repulsion field through the ship coordinate system, consider the ship's maneuverability, and set the trigger distance and potential field force gradient of the potential field in combination with the risk assessment results;

[0011] The autonomous navigation module is used to calculate the control torque of the ship based on the real-time information of the ship formation, the local environment information and the planned route information, and design an event-triggered adaptive controller to achieve collision avoidance, obstacle avoidance and communication control of the ship formation.

[0012] Preferably, the environmental information collection module includes: a waterway and hydrological information storage unit, a waterway and hydrological information reading and writing unit, and a waterway and hydrological information collection unit;

[0013] The waterway and hydrological information storage unit is used to store waterway and hydrological information near the waterway in an active RFID tag, and is installed near the waterway where the ship is sailing;

[0014] The waterway and hydrological information reading and writing unit is used to transmit a low-frequency trigger signal of information collection instructions through a trigger. When the active RFID tag enters the range of the low-frequency trigger signal, the active RFID tag generates current using its own power supply, and transmits electromagnetic wave signals of waterway and hydrological information to the RFID reader through the antenna;

[0015] The waterway and hydrological information collection unit is used to use the RFID reader to decode the received electromagnetic wave signal to obtain the waterway and hydrological information, and complete the real-time collection of the ship's navigation environment information.

[0016] Preferably, the path planning module includes: a data purification unit, a data screening unit and a route planning unit;

[0017] The data purification unit is used to pre-process the ship AIS data, remove redundant data in the ship AIS data, and complete the ship AIS data purification;

[0018] The data screening unit is used to screen and identify the core turning point data of the ship route in the ship AIS data by adopting a core turning point screening and identification method based on a particle swarm and K-means hybrid clustering algorithm;

[0019] The route planning unit is used to construct a route network based on the core turning point data through a route planning method based on an improved ant colony algorithm. In this network, the ant colony algorithm is improved through an artificial potential field method to optimize the ship route and realize ship route planning.

[0020] Preferably, the real-time information of the ship formation includes: nautical charts, meteorological information, hydrological information, channel information, and information on perceived external obstacles and neighboring ships.

[0021] Preferably, the environmental risk fusion module includes: an assessment factor determination unit, a fuzzy set establishment unit, a weight determination unit, a fuzzy relationship construction unit and a comprehensive assessment unit;

[0022] The assessment factor determination unit is used to clarify the specific object and scope of environmental risk assessment and identify the main factors affecting environmental safety;

[0023] The fuzzy set establishment unit is used to establish a corresponding fuzzy set for each evaluation factor;

[0024] The weight determination unit is used to assign corresponding weights according to the importance of each evaluation factor;

[0025] The fuzzy relationship construction unit is used to construct the fuzzy relationship between the evaluation factors based on the fuzzy set;

[0026] The comprehensive evaluation unit is used to use a fuzzy comprehensive evaluation model to comprehensively calculate the fuzzy sets and weights of various evaluation factors to obtain an overall evaluation result of the environmental risk.

[0027] Preferably, the process of establishing a ship collision avoidance and obstacle avoidance repulsion field through a ship-borne coordinate system includes:

[0028] The navigation environment information of the ship is obtained through AIS, and then the virtual dynamic target point is calculated by combining the improved dynamic order artificial potential field method;

[0029] Based on the virtual dynamic target point, the gravitational force on the ship and the repulsive force of the obstacle on the ship are superimposed to obtain the resultant force and direction for the ship's automatic collision avoidance navigation.

[0030] Preferably, the autonomous navigation module comprises: a model building unit, a position and azimuth angle measuring unit, an error calculation unit, a torque estimation unit, and a tracking control unit;

[0031] The model building unit is used to establish a virtual ship kinematic model;

[0032] The position and azimuth angle measurement unit is used to plan the target reference path according to the kinematic model of the virtual ship, generate the position time series signal of the target reference path according to the motion track of the virtual ship, obtain the position and azimuth angle information of the tracking target at the current moment, and enter the tracking control state;

[0033] The error calculation unit is used to calculate the relative position error between the real ship and the virtual ship, the real ship LOS heading angle command signal, and its first-order derivative and second-order derivative according to the current position and heading angle signal measured by the real ship;

[0034] The moment estimation unit is used to design a nonlinear disturbance observer based on a ship dynamics model to estimate the surge disturbance force, sway disturbance force and bow pitch disturbance moment;

[0035] The tracking control unit is used to design a control law according to a robust adaptive control strategy, calculate the main engine propulsion control force command signal and the bow rolling control torque command signal, and drive the real ship to track the virtual ship by controlling the main engine and the steering device, thereby finally realizing path tracking control.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention obtains real-time navigation information related to ship safety through the ship navigation system, combines the risk indicators such as wind, wave and current of the ship's environment perception information, and uses fuzzy reasoning to evaluate the ship's collision avoidance and obstacle avoidance control performance and determine the safe distance. In the process of formation control, when the ship's AIS automatic identification system equipment obtains the ship's dynamic information and determines that the distance between the ships is less than the safe formation distance or greater than the safe communication distance or the distance between the ship and the obstacle is less than the safe distance, the collision avoidance or obstacle avoidance or communication maintenance artificial potential field is triggered, and the position, heading and speed of the ship are controlled based on the event triggering and disturbance observer method through the joint action of the artificial potential field torque and the ship formation control torque, while considering the input saturation limit. The present invention effectively combines the risk identification and assessment method with the artificial potential field method, effectively utilizes the ship's navigation information and environmental risk perception wind, wave and current information, and realizes safe and efficient navigation of ships and intelligent formation control. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only 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.

[0039] Figure 1 The figure is a schematic diagram of the structure of an autonomous navigation system taking into account ship obstacle avoidance according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] Embodiment 1

[0043] like Figure 1As shown, the present invention provides an autonomous navigation system considering ship obstacle avoidance, including: an environmental information collection module, a path planning module, a real-time information collection module, an environmental risk fusion module, a potential field setting module and an autonomous navigation module;

[0044] The environmental information collection module is used to collect ship navigation environment information and ship AIS data using ship navigation equipment;

[0045] The path planning module is used to conduct risk assessment on the information collected by the ship, set the starting and ending points of the ship's voyage, formulate a specific ship's voyage path plan, and obtain the planned route information;

[0046] The real-time information acquisition module is used to obtain real-time information of the ship formation by collecting information about the ship's own status and the external environment in real time during the motion control process of executing the planned route;

[0047] The environmental risk fusion module is used to fuse environmental risks using fuzzy risk assessment methods to obtain local environmental information;

[0048] The potential field setting module is used to establish the ship collision avoidance and obstacle avoidance repulsion field through the ship coordinate system, consider the ship's maneuverability, and set the potential field trigger distance and potential field force gradient size in combination with the risk assessment results;

[0049] The autonomous navigation module is used to calculate the control torque of the ship based on the real-time information of the ship formation, local environmental information and planned route information, and use the disturbance observer to design an event-triggered adaptive controller to achieve collision avoidance, obstacle avoidance and communication control of the ship formation.

[0050] In this embodiment, the environmental information collection module includes: a waterway and hydrological information storage unit, a waterway and hydrological information reading and writing unit, and a waterway and hydrological information collection unit;

[0051] The waterway and hydrological information storage unit is used to store the waterway and hydrological information near the waterway in the active RFID tag, and is installed near the waterway where the ship is sailing;

[0052] The waterway and hydrological information reading and writing unit is used to transmit a low-frequency trigger signal of information collection instructions through a trigger. When the active RFID tag enters the range of the low-frequency trigger signal, the active RFID tag generates current using its own power supply, and transmits electromagnetic wave signals of waterway and hydrological information to the RFID reader through the antenna;

[0053] The waterway and hydrological information collection unit is used to use the RFID reader to decode the received electromagnetic wave signal, obtain the waterway and hydrological information, and complete the real-time collection of the ship's navigation environment information.

[0054] In this embodiment, the path planning module includes: a data purification unit, a data screening unit and a route planning unit;

[0055] The data purification unit is used to pre-process the ship AIS data, remove the redundant data in the ship AIS data, and complete the ship AIS data purification;

[0056] The data screening unit is used to screen and identify the core turning point data of the ship route in the ship AIS data by adopting the core turning point screening and identification method based on the particle swarm and K-means hybrid clustering algorithm;

[0057] Specifically, (1) During the process of initializing the population particles, each ship route turning point sample is arbitrarily assigned to a certain type and set as the initial clustering division; the position encoding of the initial particle is the cluster center of each data type. The particle fitness is calculated and set to the optimal individual position of the particle. The particle velocity is initialized in a non-fixed mode. The operation is repeated M times to establish M initial particle groups. (2) For each particle, its fitness needs to be compared with its optimal position and fitness, and the optimal position of this particle is identified and updated. (3) For each particle, its fitness needs to be compared with the optimal position and fitness of its group, and the global optimal position is identified and updated. (4) The speed and position of the particle need to be adjusted by the particle swarm algorithm. (5) The optimal extrapolated particle q(m+1) is obtained using the following formula: q(m+1)=q(m+1)+h(q(m+1))-q(m)+10 -6 ·rand(1), where h is the adjustment coefficient; q(m) is the current position of the particle; and rand is the rand function. (6) After increasing the mutation probability through formula (2), the particles participating in the mutation are subjected to K-means processing: if(s j <D u )thenu je =s2×s3×U max / D n (2), where s j (j∈N) is a random variable whose value range is [0, 1]; after performing fitness ranking, some particles with poor fitness are described as N; s2, s3∈s j .U max 、u je They are the current maximum particle speed and the current particle running speed in the e dimension; D n , D u is the learning factor. (7) Use formula (3) to judge the convergence of the current particle swarm. If the population fitness variance β2 is not greater than the threshold ε, use the best particle to implement the K-means local search algorithm to avoid entering the premature convergence trap. Among them, g j , g avg, g are the fitness of the jth particle, the mean of the current fitness of the particle swarm, and the current fitness of the particle swarm, respectively. M is the number of particles in the particle swarm. The best particle is optimized using the K-means local search algorithm: a. The cluster center code of the particle is set to the initial value, and the corresponding particle clustering is achieved according to the nearest neighbor rule; b. The new cluster center of the core turning point of the ship route is calculated in the clustering mode, and the original code value is replaced. Because K-means has significant local retrieval performance, the convergence efficiency of the particle swarm algorithm is improved after using K-means optimization; c. If the number of iterations is the maximum value, the fitness value of the new cluster center of the core turning point is identified. If it is better than the previous particle, the particle is updated, the iteration is stopped, and the core turning point clustering result is output. Otherwise, it returns to step b.

[0058] The route planning unit is used to construct a route network based on the core turning point data through a route planning method based on the improved ant colony algorithm. In this network, the ant colony algorithm is improved through the artificial potential field method to optimize the ship route and realize ship route planning.

[0059] Specifically, the route planning process based on the improved ant colony algorithm is: (1) Set the starting point, target point, and obstacle range in the electronic chart display information system. (2) Set the number of ants, the maximum number of iterations, the pheromone importance level, the heuristic function importance level, the pheromone concentration, the heuristic information decrease coefficient, the pheromone volatility coefficient, the path length weight, and the deviation distance weight mean. (3) Obtain the initial route and node distance information through the artificial potential field method, and use the improved ant path selection criterion to plan the subsequent route. (4) If the ant reaches the target, stop this round of circulation and update the pheromone according to the pheromone update mechanism. (5) Determine whether the number of iterations is the maximum value. If so, output the best route path. Otherwise, jump to step (3).

[0060] In this embodiment, the real-time information of the ship formation includes: nautical charts, meteorological information, hydrological information, channel information, and information on perceived external obstacles and neighboring ships.

[0061] In this embodiment, the environmental risk fusion module includes: an assessment factor determination unit, a fuzzy set establishment unit, a weight determination unit, a fuzzy relationship construction unit and a comprehensive assessment unit;

[0062] The assessment factor determination unit is used to clarify the specific object and scope of environmental risk assessment and identify the main factors affecting environmental safety;

[0063] The fuzzy set building unit is used to build a corresponding fuzzy set for each evaluation factor;

[0064] The weight determination unit is used to assign corresponding weights according to the importance of each evaluation factor;

[0065] The fuzzy relationship building unit is used to build the fuzzy relationship between evaluation factors based on the fuzzy set;

[0066] The comprehensive assessment unit is used to use the fuzzy comprehensive evaluation model to comprehensively calculate the fuzzy sets and weights of each assessment factor to obtain the overall assessment result of environmental risks.

[0067] In this embodiment, the process of establishing the ship collision avoidance and obstacle avoidance repulsion field through the ship coordinate system includes:

[0068] The navigation environment information of the ship is obtained through AIS, and then the virtual dynamic target point is calculated by combining the improved dynamic order artificial potential field method;

[0069] Based on the virtual dynamic target point, the gravitational force on the ship and the repulsive force of the obstacle on the ship are superimposed to obtain the resultant force and direction for the ship's automatic collision avoidance navigation.

[0070] Specifically, the improved dynamic-order artificial potential field method is: set the gravitational potential function to The algorithm also adds the function of avoiding static obstacles. The timing of avoiding static obstacles and the timing of restoring the track are determined by whether the ship is within the range of the obstacle. goal ) is the relative distance between the ship and the target, k2 is a positive coefficient, is the relative speed between own ship and target.

[0071] In this embodiment, the autonomous navigation module includes: a model building unit, a position and azimuth measurement unit, an error calculation unit, a torque estimation unit, and a tracking control unit;

[0072] The model building unit is used to build a virtual ship kinematic model;

[0073] The position and azimuth angle measurement unit is used to plan the target reference path according to the kinematic model of the virtual ship, generate the position time series signal of the target reference path according to the motion track of the virtual ship, obtain the position and azimuth angle information of the tracking target at the current moment, and enter the tracking control state;

[0074] The error calculation unit is used to calculate the relative position error between the real ship and the virtual ship, the real ship LOS heading angle command signal, and its first-order derivative and second-order derivative according to the current position and heading angle signal measured by the real ship;

[0075] The moment estimation unit is used to design a nonlinear disturbance observer based on the ship dynamics model to estimate the surge disturbance force, sway disturbance force and bow pitch disturbance moment;

[0076] The tracking control unit is used to design the control law according to the robust adaptive control strategy, calculate the main engine propulsion control force command signal and the bow roll control torque command signal, and drive the real ship to track the virtual ship by controlling the main engine and steering device, and finally realize path tracking control.

[0077] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. An autonomous navigation system considering ship obstacle avoidance, characterized in that: include: Environmental information collection module, path planning module, real-time information collection module, environmental risk fusion module, potential field setting module and autonomous navigation module; The environmental information collection module is used to collect ship navigation environment information and ship AIS data using ship navigation equipment; The path planning module is used to conduct risk assessment on the information collected by the ship, set the starting point and end point of the ship's navigation, formulate a specific ship's navigation path plan, and obtain the planned route information; The real-time information acquisition module is used to obtain real-time information of the ship formation by collecting information about the ship's own state and the external environment in real time during the motion control process of executing the planned route; The environmental risk fusion module is used to fuse environmental risks using a fuzzy risk assessment method to obtain local environmental information; The potential field setting module is used to establish a ship collision avoidance and obstacle avoidance repulsion field through the ship coordinate system, consider the ship's maneuverability, and set the trigger distance and potential field force gradient of the potential field in combination with the risk assessment results; The autonomous navigation module is used to calculate the control torque of the ship based on the real-time information of the ship formation, the local environment information and the planned route information, and design an event-triggered adaptive controller to achieve collision avoidance, obstacle avoidance and communication control of the ship formation.

2. The autonomous navigation system considering ship obstacle avoidance according to claim 1, characterized in that: The environmental information collection module includes: a waterway and hydrological information storage unit, a waterway and hydrological information reading and writing unit, and a waterway and hydrological information collection unit; The waterway and hydrological information storage unit is used to store waterway and hydrological information near the waterway in an active RFID tag, and is installed near the waterway where the ship is sailing; The waterway and hydrological information reading and writing unit is used to transmit a low-frequency trigger signal of information collection instructions through a trigger. When the active RFID tag enters the range of the low-frequency trigger signal, the active RFID tag generates current using its own power supply, and transmits electromagnetic wave signals of waterway and hydrological information to the RFID reader through the antenna; The waterway and hydrological information collection unit is used to use the RFID reader to decode the received electromagnetic wave signal to obtain the waterway and hydrological information, and complete the real-time collection of the ship's navigation environment information.

3. The autonomous navigation system considering ship obstacle avoidance according to claim 1, characterized in that: The path planning module includes: a data purification unit, a data screening unit and a route planning unit; The data purification unit is used to pre-process the ship AIS data, remove redundant data in the ship AIS data, and complete the ship AIS data purification; The data screening unit is used to screen and identify the core turning point data of the ship route in the ship AIS data by adopting a core turning point screening and identification method based on a particle swarm and K-means hybrid clustering algorithm; The route planning unit is used to construct a route network based on the core turning point data through a route planning method based on an improved ant colony algorithm. In this network, the ant colony algorithm is improved through an artificial potential field method to optimize the ship route and realize ship route planning.

4. The autonomous navigation system considering ship obstacle avoidance according to claim 1, characterized in that: The real-time information of the ship formation includes: nautical charts, meteorological information, hydrological information, channel information, and information on perceived external obstacles and neighboring ships.

5. The autonomous navigation system considering ship obstacle avoidance according to claim 1, characterized in that: The environmental risk fusion module includes: an assessment factor determination unit, a fuzzy set establishment unit, a weight determination unit, a fuzzy relationship construction unit and a comprehensive assessment unit; The assessment factor determination unit is used to clarify the specific object and scope of environmental risk assessment and identify the main factors affecting environmental safety; The fuzzy set establishment unit is used to establish a corresponding fuzzy set for each evaluation factor; The weight determination unit is used to assign corresponding weights according to the importance of each evaluation factor; The fuzzy relationship construction unit is used to construct the fuzzy relationship between the evaluation factors based on the fuzzy set; The comprehensive evaluation unit is used to use a fuzzy comprehensive evaluation model to comprehensively calculate the fuzzy sets and weights of various evaluation factors to obtain an overall evaluation result of the environmental risk.

6. The autonomous navigation system considering ship obstacle avoidance according to claim 1, characterized in that: The process of establishing the ship collision avoidance and obstacle avoidance repulsion field through the ship coordinate system includes: The navigation environment information of the ship is obtained through AIS, and then the virtual dynamic target point is calculated by combining the improved dynamic order artificial potential field method; Based on the virtual dynamic target point, the gravitational force on the ship and the repulsive force on the ship by the obstacle are superimposed to obtain the resultant force and direction for the ship's automatic collision avoidance navigation.

7. The autonomous navigation system considering ship obstacle avoidance according to claim 1, characterized in that: The autonomous navigation module includes: a model building unit, a position and azimuth measurement unit, an error calculation unit, a torque estimation unit, and a tracking control unit; The model building unit is used to establish a virtual ship kinematic model; The position and azimuth angle measurement unit is used to plan the target reference path according to the kinematic model of the virtual ship, generate the position time series signal of the target reference path according to the motion track of the virtual ship, obtain the position and azimuth angle information of the tracking target at the current moment, and enter the tracking control state; The error calculation unit is used to calculate the relative position error between the real ship and the virtual ship, the real ship LOS heading angle command signal, and its first-order derivative and second-order derivative according to the current position and heading angle signal measured by the real ship; The moment estimation unit is used to design a nonlinear disturbance observer based on a ship dynamics model to estimate the swell disturbance force, the sway disturbance force and the bow pitch disturbance moment; The tracking control unit is used to design a control law according to a robust adaptive control strategy, calculate the main engine propulsion control force command signal and the bow rolling control torque command signal, and drive the real ship to track the virtual ship by controlling the main engine and the steering device, thereby finally realizing path tracking control.

Images