A remote control method and system for unmanned ship

Abstract

The invention discloses a method and system for remotely controlling an unmanned ship. The method expands by screening jump points until a final path is generated, and uses jump points to replace unnecessary nodes in an A* algorithm. On the basis of a traditional VFH algorithm, the method can avoid colliding with obstacles while jumping out of a local dead loop, and formulate a global optimal path for the unmanned ship. In the path tracking stage, a local path for avoiding obstacles is formulated. Based on the improved LOS line of sight guidance and on the basis of the PID control principle, a guidance law with integral and differential terms is provided, and pre-steering control and speed control optimization are added. The remote control system of the unmanned ship comprises: a shore-based ground station command system, a 5G network communication module, a control decision module, an intelligent navigation module, a sensor module, an electronic nautical chart, a path planning module, a motion control module, and an energy and power module, which greatly improves the communication control distance of the unmanned ship, controls the unmanned ship to complete the path tracking function, and effectively improves the intelligence level of the unmanned ship.

Description

Technical Field

[0001] The present invention relates to the technical field of ship equipment, and in particular to a remote control method and system for an unmanned ship. Background Art

[0002] With the development of intelligent technology and the deepening of the development of marine resources in various countries around the world, surface unmanned ships have received more attention and development. Unmanned ships are intelligent platforms that rely on ship-borne sensor equipment to move on the water surface in an autonomous or semi-autonomous manner. By carrying different equipment, they can perform tasks such as water environment mapping, marine resource surveys, marine archaeology, marine environmental protection, surface search and rescue, fire strikes, anti-mine, and anti-submarine, and have been widely used in civil and military fields. Compared with traditional manually operated ships, unmanned ships have higher navigation accuracy and more stable operation effects, and have outstanding advantages in some special environments. Therefore, with the increasing maturity of intelligent technology, network technology and unmanned ship driving technology, unmanned ships have received more attention.

[0003] At present, the control communication of unmanned ships often adopts point-to-point or local area network signal communication methods, which have good effects in short distances and with few surrounding obstacles. However, when the distance exceeds a certain limit or there are large obstacles in the navigation area of ​​the unmanned ship, the communication signal effect drops significantly and cannot meet the needs of real-time motion control of the unmanned ship. As shown in publication number CN114394202A, the system of installing signal transceivers using cables to realize communication control of unmanned ships is cumbersome and complicated to realize communication through cables, and the cable length cannot be accurately controlled, and the communication distance is also limited. As shown in publication number CN 113156960A, the wireless link is constructed using a local area network device to realize the communication control of unmanned ships. The transmission bandwidth of the wireless link is limited, and it gradually weakens with the increase of the navigation distance, so that the communication is disconnected or the communication quality is greatly reduced.

[0004] At the same time, the path planning and autonomous obstacle avoidance of unmanned ships are one of the key technologies for performing autonomous tasks. The accuracy of path tracking and the ability of autonomous obstacle avoidance reflect the intelligence level of unmanned ships.

[0005] The current unmanned ship remote control technology mainly adopts point-to-point wireless communication technology or local area network communication technology, which results in the transmission of only simple control data, poor communication real-time performance, few types of data that can be collected, and limited data transmission distance. In addition, traditional algorithms have high computing power overhead and long calculation time in the path-finding process, which cannot meet the real-time requirements of unmanned ships in path planning in larger scenarios. In addition, the autonomy of unmanned ship motion control is low and the navigation route is not optimal. The obstacle avoidance path of the unmanned ship in the traditional algorithm is poor and easy to fall into an infinite loop. The current traditional algorithm has complex guidance laws, difficult parameter calibration, and a narrow range of use, which affects the path tracking of the unmanned ship. Summary of the invention

[0006] The purpose of the present invention is to address the shortcomings of the prior art and provide a method and system for remote control of an unmanned ship. The method uses 5G communication technology as a communication link, the Internet of Things platform as a service platform, and an improved A* algorithm and VFH algorithm to enable the unmanned ship to obtain a better navigation route and obstacle avoidance route. At the same time, based on the improved LOS line of sight guidance, the unmanned ship path tracking is completed to achieve a stable, efficient and safe remote control effect of the unmanned ship.

[0007] A method for remotely controlling an unmanned ship, comprising the following steps:

[0008] S1. The unmanned boat starts after passing the self-inspection;

[0009] S2, obtain the spatiotemporal data T of the unmanned ship at the current moment, and send it to the shore-based ground station command system through the 5G network communication module;

[0010] S3, set the target node g and the return point H for the unmanned ship on the shore-based ground station command system, set the control decision mode through the control decision module, and send it to the unmanned ship through the 5G network communication module;

[0011] S4. After receiving the data from the shore-based ground station command system, the intelligent navigation module obtains the spatiotemporal data of the unmanned ship at the next moment T+1, and uses the offline electronic chart data to build and update the water environment model based on the fusion of the data obtained by the sensor module;

[0012] S5. Perform path planning between the ship position and the target node g in the spatiotemporal data T+1 of the next moment of the unmanned ship, and formulate the best navigation route for the unmanned ship, specifically:

[0013] The improved A* algorithm is used for global path planning. Specifically, the A* algorithm is optimized by combining the jump point search algorithm. In the path finding process, the A* algorithm uses jump points to replace a large number of unnecessary nodes in the A* algorithm, and expands by screening jump points until the final path is generated.

[0014] The improved VFH algorithm is used for local path planning, specifically: adaptive sector threshold optimization is performed, by setting appropriate thresholds to screen the passable sectors of the unmanned ship, obstacles are divided into different priorities through obstacle information detected by the sensor module, and adaptive thresholds are calculated to set different thresholds for different obstacles; the dead loop optimization of the improved cost function is performed, by predicting the dead loop of all candidate directions, and using different cost functions for different candidate directions to select the optimal obstacle avoidance direction;

[0015] S6. After obtaining the best navigation route calculated by the intelligent navigation module, the motion control module uses the PID control method to realize the motion control of the unmanned ship on the basis of improving the LOS line of sight guidance. By optimizing the heading control and speed control, the path of the unmanned ship is tracked to realize the control of the autonomous navigation of the unmanned ship.

[0016] S7. Calculate the safe distance of the ship based on the real-time scanning information of the laser radar. If the other ship and the own ship maintain a safe distance or the waters are passable, the own ship continues to sail along the original route; when the distance between the other ship and the own ship is less than the safe distance or the waters are impassable, the intelligent navigation module formulates an obstacle avoidance route and hands it over to the motion control module for immediate execution; if the obstacle avoidance route cannot be formulated in time, the emergency obstacle avoidance function will be triggered, and the vehicle will brake or move in the opposite direction immediately for emergency avoidance; the shore-based ground station command system can take over the control authority of the unmanned ship in an emergency, and the unmanned ship will be controlled manually to complete the avoidance action;

[0017] S8, 5G network communication module is used to keep the unmanned ship connected to the shore-based ground station command system over long distances, and send the unmanned ship's spatiotemporal data T to the shore-based ground station command system at a certain frequency. The shore-based ground station command system monitors the navigation status of the unmanned ship in real time.

[0018] Furthermore, the specific steps of using the improved A* algorithm to perform global path planning in S5 are:

[0019] S51. In the map grid, add the starting node s to OpenList, f(s) = h(s), ClosedList is used to save the nodes that have been searched, f(s) is the cost function of the A* algorithm, which represents the cost of reaching the target node g from the starting point s via any node n, and h(s) represents the heuristic function of the A* algorithm, which represents the estimated cost from node n to the target node g;

[0020] S52, if OpenList is empty, the path finding fails and ends, otherwise enter S53;

[0021] S53, calculate the node with the smallest f(s) value in OpenList, delete the node from OpenList, and add it to ClosedList;

[0022] S54, if the current node is the target node g, the path finding is successful and ends, otherwise enter S55;

[0023] S55, according to the direction of the target node g, expand in the horizontal and vertical directions, and if an obstacle is encountered or the map boundary is reached, expand in the diagonal direction;

[0024] S56. If a jump point is detected, the jump point is added to the OpenList and S53 to S56 are looped. If no jump point is detected, the node is ignored and S55 to S56 are looped.

[0025] Furthermore, the adaptive sector threshold optimization in the local path planning using the improved VFH algorithm in S5 is specifically as follows:

[0026] M i =λ 1 ·M max +λ 2 ·M mmin

[0027] In the formula, λ 1 ·M max is the target priority, λ 2 ·M mmin Safety is a priority, and M min <M max , M i is the adaptive threshold of the i-th sector, M max and M mmin The value range is: M L >M≥M D , M L Indicates the threshold value of the maximum scanning distance of the dangerous distance radar, M D Indicates the safe distance threshold for avoiding obstacles.

[0028] Furthermore, the improved VFH algorithm is used in S5 to perform the dead loop optimization of the improved cost function in the local path planning as follows:

[0029] For candidate directions that are not in danger of falling into an infinite loop, set the following cost function:

[0030] G=μ 1 Δ(c i , k t )+μ 2 Δ(c i , k n )+μ 3 Δ(c i , g c )

[0031] For candidate directions that are in danger of falling into an infinite loop, set the following cost function:

[0032] G′=μ 1 Δ(c i , k n )+μ 2 Δ(c i , g c )

[0033] In the formula, μ 1 , μ 2 , μ 3 represents a constant, c i represents the candidate direction, k t Indicates the current heading of the unmanned ship, k n represents the last heading of the unmanned ship, g c Indicates the last heading of the unmanned ship.

[0034] Furthermore, the S6 is specifically:

[0035] Use PID control method to control the speed of unmanned boat:

[0036]

[0037] The PID control method is used to control the heading of the unmanned ship:

[0038]

[0039] The control system formula of the unmanned ship is obtained:

[0040]

[0041] In the formula, e v (t) is the difference between the actual speed and the target speed, e v (t-1) is the difference between the last calculation time and P v (t) is the output value of speed control, K p is the proportional gain in the PID controller, K d is the differential gain in the PID controller, e a (t) is the difference between the actual heading and the target heading, ω is the heading angular velocity obtained after filtering and noise reduction of the measured angular velocity, F x is the longitudinal thrust of the unmanned ship, F l 、F r is the thrust generated by the left and right motors of the unmanned ship, F d is the lateral resistance of the unmanned ship during movement, M d represents the moment on the unmanned ship, l o is the distance between the two propellers of the unmanned ship, H represents the comprehensive lateral force of the unmanned ship, and the speeds of the two motors are n l and n r .

[0042] Furthermore, the spatiotemporal data T of the unmanned ship in S2 includes: the current navigation positioning information of the unmanned ship, the hull posture information of the unmanned ship, the depth of field information of the water environment where the unmanned ship is located, the lidar scanning information, the battery information, and the image information of the water environment where the unmanned ship is located.

[0043] Furthermore, the water environment model in S4 is constructed specifically as follows: by acquiring the spatiotemporal data of the unmanned ship, fusing it with the data acquired by the sensor module, and combining it with the offline electronic nautical chart, a water environment map is constructed, the area where the unmanned ship is located is divided into a number of grids, and a grid map is created using the grid method.

[0044] Based on the same inventive concept, the present invention provides an unmanned ship remote control system, including a shore-based ground station command system and a ship-side system. The shore-based ground station command system is used for unmanned ship mission dispatching, unmanned ship status monitoring and manual control, and the ship-side system includes:

[0045] The 5G communication module is used to realize long-distance cross-end communication between the unmanned ship and the shore-based ground station command system, and to achieve long-distance task distribution of the unmanned ship and ship-side data reception;

[0046] The control decision module is used to control the unmanned ship to achieve different control modes, including autonomous navigation mode, manual control mode, and emergency obstacle avoidance mode;

[0047] The intelligent navigation module includes a sensor module, an electronic nautical chart, and a path planning module. The sensor module is used to collect the spatiotemporal data of the unmanned ship at the current moment and update the water environment model; the electronic nautical chart is used to provide accurate basic environmental data for the autonomous navigation of the unmanned ship and to construct an initial water environment model; the path planning module executes the path planning method of the above-mentioned unmanned ship remote control method, uses the improved A* algorithm, replaces unnecessary nodes in the A* algorithm with jump points, and expands by screening jump points until the final path is generated to achieve global path planning, uses the improved VFH path planning algorithm, realizes local path planning through adaptive sector threshold optimization and improved cost function dead loop optimization, and smoothes the route obtained by path planning to provide a smoother route for the unmanned ship;

[0048] The motion control module realizes the motion control of the unmanned ship through the PID control method based on the path obtained by the intelligent navigation module and on the basis of improving the LOS line of sight guidance;

[0049] The energy power module is used to provide power for the unmanned ship and provide battery information for decision-making on whether the mission can be completed normally.

[0050] Based on the same inventive concept, the present invention provides an unmanned ship remote control device, the device comprising:

[0051] A memory storing executable program code;

[0052] a processor coupled to the memory;

[0053] The processor calls the executable program code stored in the memory to execute the above-mentioned unmanned ship remote control method.

[0054] Based on the same inventive concept, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the above-mentioned unmanned ship remote control method.

[0055] Beneficial effects of the present invention:

[0056] (1) The present invention proposes a method and system for remote control of an unmanned ship, and designs an unmanned ship remote control system based on 5G communication technology. Through 5G communication technology, the communication control distance of the unmanned ship can be greatly improved, and the unmanned ship can be controlled to complete tasks over long distances and in harsh environments.

[0057] (2) The present invention proposes an unmanned ship remote control method and system, and proposes an improved A* algorithm and an improved VFH algorithm. The improved A* algorithm can achieve long-distance jumps by connecting jump points, so only a short time is needed for preprocessing during the path finding process, thereby greatly reducing the operation time of OpenList and ClosedList, and effectively reducing the computing power overhead during the path finding process. The improved A* algorithm can significantly improve the path finding speed and reduce the computing power overhead while ensuring the generation of the most efficient path, especially in larger path planning scenarios. For the threshold-sensitive characteristics of the traditional VFH algorithm, an adaptive sector threshold function is designed. By dividing obstacles into different priorities, as many obstacle avoidance paths as possible are found to ensure the smoothness of the obstacle avoidance path. The traditional cost function is improved by predicting in advance the signs that the unmanned ship will fall into a local dead loop, changing the priority of the obstacle avoidance direction selection, and ensuring that when the unmanned ship falls into a dead loop, it can avoid colliding with obstacles while jumping out of the local dead loop and find a path to the target point. In the path tracking stage, based on the update of the water environment model, a local path for obstacle avoidance is formulated for the unmanned ship, and then the optimal navigation route is formulated for the unmanned ship. On the basis of the PID control principle, the LOS line of sight controller is improved. Integral and differential terms are added to the conventional LOS guidance law. On the basis of keeping the structure of the LOS guidance law simple, pre-steering control and speed control optimization are added, which has a good control effect on the differential unmanned ship. The improved LOS guidance law has improvements in control error, stability and anti-interference, and improves the fast convergence performance, thereby controlling the unmanned ship to complete the path tracking function, realizing the autonomous navigation of the unmanned ship, and effectively improving the intelligence of the unmanned ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to further understand the features and technical contents of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings are only provided for reference and illustration and are not intended to limit the present invention.

[0059] Figure 1 is a flow chart of a method for remote control of an unmanned ship;

[0060] Figure 2 This is a flowchart of global path planning using the improved A* algorithm;

[0061] Figure 3 This is a schematic diagram of the jump point search algorithm;

[0062] Figure 4 This is a schematic diagram of the unmanned ship's guidance process using the LOS line of sight method;

[0063] Figure 5 A schematic diagram of a remote control system for an unmanned ship. DETAILED DESCRIPTION

[0064] See also Figures 1 to 5 The embodiment of the present invention provides a method and system for remotely controlling an unmanned ship, which specifically includes the following contents:

[0065] The unmanned ship remote control method of the present invention is as follows: Figure 1 As shown, specifically including:

[0066] First, start the unmanned boat, and the operator checks whether the hull of the unmanned boat and the equipment on board are normal, turns on the power switch of the unmanned boat, and the equipment starts working.

[0067] Then, the spatiotemporal data T of the unmanned ship at the current moment is obtained and sent to the shore-based ground station command system through the 5G network communication module. The spatiotemporal data T of the unmanned ship includes: the current navigation positioning information of the unmanned ship, hull attitude information, laser radar scanning information, battery information, image information and other data.

[0068] The target node g and return point H are set for the unmanned ship on the shore-based ground station command system, and the control decision mode is set through the control decision module and sent to the unmanned ship through the 5G network communication module.

[0069] After receiving the data from the shore-based ground station command system, the intelligent navigation module obtains the spatiotemporal data of the unmanned ship at the next moment T+1, and uses the offline electronic chart data to build and update the water environment model based on the fusion of multiple sensor data obtained by the sensor module. By obtaining the unmanned ship's environmental data and fusing the sensor data, combined with the offline electronic chart, the water environment map is constructed, the area where the unmanned ship is located is divided into several grids, and the grid map is created using the grid method.

[0070] Furthermore, the improved A* algorithm and the improved VFH algorithm are used to specify the best navigation route between the ship position and the target position g in the spatiotemporal data T+1 of the next moment of the unmanned ship. Including: expanding by screening jump points until the final path is generated, using jump points to replace a large number of unnecessary nodes that may be added to the OpenList and ClosedList in the A* algorithm during the expansion process, thereby reducing the amount of calculation and effectively reducing the computing power overhead in the path-finding process. At the same time, based on the traditional VFH algorithm, the traditional cost function is improved, and the priority of obstacle avoidance direction selection is changed by predicting in advance the signs that the unmanned ship will fall into a local dead loop, ensuring that when the unmanned ship falls into a dead loop, it can avoid colliding with obstacles and jump out of the local dead loop. Therefore, a global optimal path is first formulated for the unmanned ship, and then in the path tracking stage, a local path for obstacle avoidance is formulated for the unmanned ship based on the update of the environmental model, and then the best navigation route is formulated for the unmanned ship.

[0071] Specifically, the A* algorithm is improved from the following aspects:

[0072] (1) Optimize the A* algorithm search strategy by combining the jump point search algorithm

[0073] The Jump Point Search algorithm (JPS for short) is a search strategy, where a jump point is a node that can be directly jumped during the search process. Figure 3 As shown in the figure, there are three paths from node s to node g, namely: s→a2→g, s→b2→g, and s→c2→g. In the process of path finding, the A* algorithm compares the estimated value of each node on the path and selects the node with the lowest cost (b2). This process requires visiting and operating each adjacent node (a2, b2, c2). Obviously, it is meaningless to evaluate the two nodes a2 and c2, because in this case, the cost of the path s→b2→g is always the lowest. In order to further improve the search speed, the search can be performed directly according to the direction of the parent node (i.e., node g). This is the search strategy of the jump point search algorithm. Jump point search is to select certain specific nodes in the process of expanding nodes instead of evaluating all adjacent nodes for expansion. These selected nodes are called jump points. The g node in the figure is a jump point (the path here is short enough, and other path segments are ignored). The intermediate nodes on the path composed of two jump points will not be expanded, which also greatly reduces the amount of calculation and storage in the expansion process, thereby effectively reducing the amount of calculation and memory consumption of the algorithm in the path finding process.

[0074] (2) Improving the A* algorithm pathfinding process

[0075] like Figure 2As shown in the figure, in the map grid, s represents the starting node and g represents the target node. First, the starting node s is added to the OpenList (to save the nodes that have been searched), and it is expanded in the horizontal and vertical directions (the expansion direction depends on the direction from the parent node to the current node. When the parent node does not exist, it is expanded in the horizontal and vertical directions first) until an obstacle is encountered or the edge of the map is reached. At this time, it starts to expand along the diagonal. When expanding to a new node along the diagonal, it continues to expand in the horizontal and vertical directions, and repeats this process until the vertical expansion reaches the edge of the map. The horizontal expansion finds a mandatory neighbor node. At this time, the mandatory neighbor node is added to the OpenList. The mandatory neighbor node continues to expand to the right as a jump point until the edge of the map is reached. At this time, it continues to expand along the diagonal. During the expansion process, the next mandatory neighbor node is found, added to the OpenList and continued to expand in the horizontal and vertical directions as a new jump point until the target point is found. At this time, the iteration is stopped, the target point is added to the OpenList, and the final path is obtained.

[0076] Specifically, the specific steps of using the improved A* algorithm for global path planning are as follows:

[0077] S51. In the map grid, add the starting node s to OpenList, f(s) = h(s), ClosedList is used to save the nodes that have been searched, f(s) is the cost function of the A* algorithm, which represents the cost of reaching the target node g from the starting point s via any node n, and h(s) represents the heuristic function of the A* algorithm, which represents the estimated cost from node n to the target node g;

[0078] S52, if OpenList is empty, the path finding fails and ends, otherwise enter S53;

[0079] S53, calculate the node with the smallest f(s) value in OpenList, delete the node from OpenList, and add it to ClosedList. The A* algorithm will select the node with the smallest cost value in OpenList as the next expansion node, and search from the expansion node to the subsequent nodes. At this time, the node has been searched, so it needs to be deleted from OpenList and added to ClosedList for storage;

[0080] S54, if the current node is the target node g, the path finding is successful and ends, otherwise enter S55;

[0081] S55, according to the direction of the target node g, expand in the horizontal and vertical directions, and if an obstacle is encountered or the map boundary is reached, expand in the diagonal direction;

[0082] S56. If a jump point is detected, the jump point is added to the OpenList and S53 to S56 are looped. If no jump point is detected, the node is ignored and S55 to S56 are looped.

[0083] Specifically, in local path planning, the VFH algorithm is improved from the following aspects:

[0084] (1) Adaptive sector threshold optimization

[0085] The VFH algorithm selects passable sectors by setting appropriate thresholds, so setting appropriate thresholds is the key to successful obstacle avoidance. It is feasible to set a more reasonable threshold based on experience and actual conditions in a specific environment. If the environment around the unmanned ship changes, the threshold will no longer be suitable. Obstacle information detected by sensors is used to divide obstacles into different priorities. By continuously changing the adaptive threshold coefficient, different thresholds are set for different obstacles, avoiding the defects of premature obstacle avoidance and untimely obstacle avoidance. The calculation of the adaptive threshold is as follows:

[0086] M i =λ 1 ·M max +λ 2 ·M min

[0087] In the formula, λ 1 ·M max is the target priority, λ 2 ·M min Safety is a priority, and M min <M max , M i is the adaptive threshold of the i-th sector. max and M min The value of is mainly determined by two factors: the effective range of the sensor and the inertia of the hull.

[0088] The threshold value of the maximum scanning distance of the dangerous distance radar is obtained by the following formula.

[0089] M L =c·v 2 ·b·L 2

[0090] Where M L Indicates the threshold value at the maximum scanning distance of the dangerous distance radar, L is the maximum scanning distance of the radar, c is a constant, v is the longitudinal speed of the unmanned ship, c·v 2 The probability value selected for the grid indicates the credibility of the existence of obstacles in the grid control. b is a constant, generally defined as 0.25.

[0091] The safe distance threshold for avoiding obstacles is obtained by the following formula.

[0092]

[0093] Where M D represents the safe distance threshold for avoiding obstacles, v is the longitudinal speed of the unmanned ship, and a is the maximum longitudinal acceleration of the unmanned ship. Based on the above analysis, we can get M max and M min The value range is: M L >M≥M D , M is the safe distance that can be screened.

[0094] (2) Improving the dead loop optimization of the cost function

[0095] When the path obstacle avoidance based on VFH falls into an infinite loop, the obstacle avoidance directions selected twice are almost opposite. Therefore, it is only necessary to judge that the difference between the first obstacle avoidance direction and the second obstacle avoidance direction is basically the same as the difference between the third obstacle avoidance direction and the second obstacle avoidance direction, which can prove that the unmanned ship is about to fall into a local infinite loop and be predicted by the following formula:

[0096]

[0097] In the formula, f c Indicates the sign of falling into an infinite loop, 0 means there is no danger of an infinite loop, and 1 means it is about to fall into an infinite loop; Δ(c i , g c ) represents the angle difference between the candidate direction and the last obstacle avoidance direction; Δ(g c-1 , g c ) represents the angular difference between the last obstacle avoidance direction and the last obstacle avoidance direction, and Δg represents the error value of the dead loop.

[0098] By predicting the infinite loop of all candidate directions, different cost functions are used for different candidate directions to select the optimal obstacle avoidance direction. For candidate directions that are not in danger of falling into an infinite loop, the goal should be to stay close to the planned route, that is, the unmanned ship should give priority to the obstacle avoidance direction close to the target direction to ensure that the unmanned ship gradually approaches the target position, so the following cost function is set:

[0099] G=μ 1 Δ(c i , k t )+μ 2 Δ(c i , k n )+μ 3 Δ(c i , g c )

[0100] For candidate directions that are in danger of falling into an infinite loop, the obstacle avoidance direction that is close to the heading and away from obstacles should be selected with the purpose of ensuring the safety of the unmanned ship. When the target point direction appears in the candidate directions, it indicates that the unmanned ship has escaped the influence of the obstacle, and the infinite loop mark is reset. The cost function used in the infinite loop is:

[0101] G′=μ 1 Δ(c i , k n )+μ 2 Δ(c i , g c )

[0102] In the above formula, μ 1 , μ 2 , μ 3 represents a constant, c i represents the candidate direction, k t Indicates the current heading of the unmanned ship, k n represents the last heading of the unmanned ship, g c Indicates the last heading of the unmanned ship.

[0103] Furthermore, after obtaining the navigation route calculated by the intelligent navigation module, the motion control module improves the LOS line-of-sight guidance, including: on the basis of the PID control principle, the line-of-sight controller is improved to obtain a guidance law with integral and differential terms, and then pre-steering control and speed control optimization are added. It has a better control effect on the differential unmanned ship, and has improvements in control error, stability and anti-interference, and improves the rapid convergence performance, thereby controlling the unmanned ship to complete the path tracking function and realize autonomous navigation of the unmanned ship.

[0104] Specifically, Figure 4 As shown in the figure, the motion control module realizes the autonomous navigation of the unmanned ship by completing the path tracking function. The basic process is: according to the basic principle of LOS line of sight guidance, a forward-looking target point is set for the unmanned ship, and the expected heading of the unmanned ship at the next moment is obtained by the forward-looking target point and the next waypoint, which is obtained by the following formula.

[0105] α=β-tan -1 ((y e +k i y int ) / l)

[0106] Where β is the path direction and l is the forward distance. Both are constants in the guidance process. -1 ((y e +k i y int ) / l), the distance y from the unmanned boat to the path eand int is the input parameter that determines the desired heading, where y int is the deviation y e The integral term related to this is used to eliminate static error, k i / l can be regarded as the integral term coefficient, y e It can be regarded as a proportional term. On this basis, adding a differential term plays a role in pre-controlling system changes. The actual guidance formula is:

[0107]

[0108] In the formula, k d is the guidance law differential parameter, y eold is the path deviation of the unmanned ship at the last moment, Can be regarded as a scale parameter, k i is the integration parameter.

[0109] The PID control method is used to realize the motion control of the unmanned boat. The motion of the unmanned boat can be decomposed into forward and backward and turning motion. Therefore, the forward and turning controllers are designed separately and then integrated into the power system. The desired power of the left and right motors obtained by PID control is used to control the rotation of the left and right motors respectively to realize the motion control of the unmanned boat. The forward control of the unmanned boat becomes speed control. The calculation formula of the speed control PID is:

[0110]

[0111] In the formula, e v (t) is the difference between the actual speed and the target speed, e v (t-1) is the difference between the last calculation time and P v (t) is the output value of speed control, K p is the proportional gain in the PID controller, K d is the derivative gain in the PID controller.

[0112] The steering control of the unmanned ship is heading control, and the calculation formula of the heading control PID is:

[0113]

[0114] In the formula, e a (t) is the difference between the actual heading and the target heading, ω is the heading angular velocity obtained after filtering and noise reduction of the measured angular velocity, e a (t)-e a (t-1) is the angle at adjacent moments, and the difference between the two is equal to the angular velocity. The control system formula of the unmanned ship can be obtained:

[0115]

[0116] F x is the longitudinal thrust of the unmanned ship, F l 、F r is the thrust generated by the left and right motors of the unmanned ship, F d is the lateral resistance of the unmanned ship during movement, M d represents the moment on the unmanned ship, l o is the distance between the two propellers of the unmanned boat, and H represents the combined lateral force of the unmanned boat. The turning of the unmanned boat is determined by the difference in thrust between the two propellers, while the longitudinal motion is determined by the resultant force. The speed of the two motors n can be obtained l and n r Control formula. According to the desired speed n l and n r It is converted into an electronic speed control signal to control the speed of the left and right motors to achieve path tracking of the unmanned ship.

[0117] Then, in the path tracking stage, the safe distance of the ship is calculated based on the real-time scanning information of the laser radar. If the other ship and the ship can maintain a safe distance, or the water conditions are passable, the ship does not need to change its own route and continues to sail along the original navigation path; when the distance between the other ship and the ship is less than the safe distance, or the water conditions are impassable, the intelligent navigation module will quickly formulate an obstacle avoidance route for the ship and hand it over to the motion control module for immediate execution; if the obstacle avoidance route cannot be formulated in time, the emergency obstacle avoidance function will be triggered, and the brakes or reverse movements will be immediately applied for emergency avoidance; the data of the unmanned ship will be sent to the command system of the shore-based ground station in real time. The command system can also immediately take over the control authority of the unmanned ship in an emergency, and the unmanned ship will be manually controlled to complete the avoidance action.

[0118] Finally, the unmanned ship maintains a long-distance connection with the shore-based ground station command system through the 5G network communication module, and sends the unmanned ship's spatiotemporal data to the command system at a certain frequency. The command system can monitor the navigation status of the unmanned ship in real time.

[0119] The present invention provides an unmanned ship remote control system, such as Figure 5As shown, it includes a shore-based ground station command system and a ship-side system, wherein the ship-side system includes a 5G network communication module, a control decision module, an intelligent navigation module, a sensor module, an electronic chart, a path planning module, a motion control module, and an energy and power module. The shore-based ground station command system is used for unmanned ship mission issuance, unmanned ship status monitoring, and manual control; the shore-based ground station command system issues control instructions to the unmanned ship through the 5G network communication module and sets the control mode for the unmanned ship control decision module. In general, the unmanned ship control decision mode is set to the autonomous navigation mode. After the command system sets the target point and return point for the unmanned ship, the intelligent navigation module sets the navigation path for the unmanned ship, and the motion control module completes the path tracking function. At the same time, the unmanned ship sends the latest spatiotemporal data to the shore-based command system in real time, and the command system monitors the navigation status of the unmanned ship in real time. The 5G communication module is used to realize long-distance cross-terminal communication between the unmanned ship and the shore-based ground station command system, realize the long-distance task issuance of the unmanned ship and the ship-side data reception; realize the real-time monitoring of the navigation status of the unmanned ship by the shore-based command system; send the control instructions of the shore-based command system to the unmanned ship in real time to realize the remote and timely control of the unmanned ship. The control decision module is used to control the unmanned ship to implement different control logics. The control decision module sets different working modes for the unmanned ship, which is responsible for the autonomous navigation function of the unmanned ship and the manual control mode and the realization of emergency obstacle avoidance function. The intelligent navigation module is the core of the system, providing autonomous navigation function support for the unmanned ship, including sensor module, electronic chart, and path planning module. On the basis of offline electronic charts, the spatiotemporal data of the unmanned ship at the current moment obtained by the perception system composed of multiple sensors is used to update the water environment model. The spatiotemporal data includes: navigation and positioning data of the unmanned ship, hull attitude data, image data of the water area, obstacle data around the hull, and battery power data; the electronic chart is used to provide accurate basic environmental data for the autonomous navigation of the unmanned ship, and is used to build the initial water environment model; the path planning module is used to provide the main navigation path for the unmanned ship, including global path planning, local path planning and path optimization. Among them, the global path planning uses the improved A* global path planning algorithm to provide a main route for the unmanned ship; the local path planning uses the improved VFH path planning algorithm to provide a route for obstacle avoidance for the unmanned ship when it encounters an inaccessible obstacle; the path optimization uses the cubic B-spline curve method to smooth the route obtained by the path planning, providing a smoother route for the unmanned ship. The motion control module completes the path tracking motion function based on the path obtained by the intelligent navigation module on the basis of the improved LOS line of sight guidance.The motion control module follows the global path and autonomously navigates according to the improved LOS line of sight guidance algorithm to complete the path tracking function. The DC motor speed is regulated by the PID control algorithm. During this period, the water environment map is updated according to the spatiotemporal data of the unmanned ship. If an unreachable situation occurs, the local path planning in the path planning module uses the improved VFH algorithm to build a local path for obstacle avoidance for the unmanned ship, and the motion control module controls the unmanned ship to avoid obstacles. The energy power module is used to provide a power source for the unmanned ship and provide battery information for decision-making on whether the task can be completed normally.

[0120] The improvement of the A* global planning algorithm includes: expanding by screening jump points until the final path is generated. During the expansion process, jump points are used to replace a large number of unnecessary nodes that may be added to the OpenList and ClosedList in the A* algorithm, thereby reducing the amount of calculation and effectively reducing the computing power overhead in the path-finding process;

[0121] The improved VFH algorithm includes: improving the traditional cost function, predicting in advance the chassis where the unmanned ship will fall into a local dead loop, changing the priority of obstacle avoidance direction selection, and ensuring that when the unmanned ship falls into a dead loop, it can avoid colliding with obstacles and jump out of the local dead loop;

[0122] The improvement of LOS line-of-sight guidance includes: based on the PID control principle, the line-of-sight controller is improved to obtain a guidance law with integral and differential terms, and then pre-steering control and speed control optimization are added. It has a better control effect on the differential unmanned ship, and has improvements in control error, stability and anti-interference, and improves the rapid convergence performance.

[0123] In the manual control mode, the unmanned ship sends status information back to the shore-based ground station command system. After receiving the status information of the unmanned ship, the shore-based ground station command system controls the unmanned ship to perform motion control and obstacle avoidance.

[0124] In the one-key return mode, the unmanned boat will plan a path from the current position to the return point according to the return position set by the shore-based ground station command system, and hand it over to the motion control module for path tracking control. In addition, under normal circumstances, when the power of the unmanned boat is insufficient to complete the autonomous navigation mission, the one-key return mode can be automatically triggered to avoid the loss of the unmanned boat and improve the navigation safety performance of the unmanned boat.

[0125] The perception system composed of multiple sensor modules is used to obtain the spatiotemporal data of the unmanned ship at the current moment. The spatiotemporal data include: navigation and positioning data of the unmanned ship obtained by GPS, such as longitude, latitude, heading to the ground, speed to the ground, etc.; hull posture data of the unmanned ship obtained by IMU, such as heading angle, pitch angle, roll angle, angular velocity, etc.; obstacle depth data obtained by binocular camera; water environment image obtained by gimbal camera; obstacle information around the unmanned ship obtained by lidar; battery charge and power data obtained by BMS sensor.

[0126] Based on the same inventive concept, an unmanned ship remote control device of the present invention may include: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the steps in the above-mentioned unmanned ship remote control method.

[0127] The memory may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the memory may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). A program / utility having a set (at least one) of program modules may be stored in, for example, the memory, such program modules including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include the implementation of a network environment. The program modules typically perform the functions and / or methods in the embodiments described herein.

[0128] The processor executes various functional applications and data processing by running the programs stored in the memory, such as implementing a remote control method for an unmanned ship provided by the present invention.

[0129] Based on the same inventive concept, a computer-readable storage medium of the present invention stores computer instructions, and when the computer instructions are called, they are used to execute the unmanned ship remote control method as described above.

[0130] Computer-readable storage media can use any combination of one or more computer-readable media. Computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0131] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0132] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0133] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0134] In summary, the present invention proposes a remote control method and system for unmanned ships, designs an unmanned ship remote control system based on 5G communication technology, and through 5G communication technology, can greatly improve the communication control distance of unmanned ships, and can control unmanned ships to complete long-distance and harsh environment tasks. The present invention proposes a remote control method and system for unmanned ships, and proposes an improved A* algorithm and an improved VFH algorithm. For the improved A* algorithm, a preprocessing process is added on the basis of the A* algorithm in combination with the jump point search, that is, some representative jump points are selected by the jump point search algorithm, and then the jump points are added to the OpenList for calculation, so that the traditional A* algorithm avoids the calculation of a large number of intermediate nodes during the algorithm path finding process. Different from the traditional A* algorithm, which can only explore and plan a small step at a time, the improved A* algorithm can achieve a longer distance jump by connecting jump points, so only a short time is needed for preprocessing during the path finding process, thereby greatly reducing the operation time of OpenList and ClosedList, and effectively reducing the computing power overhead during the path finding process. Compared with the traditional A* algorithm, which has the disadvantages of high computing power and long calculation time in the path-finding process, and cannot meet the real-time requirements of unmanned ships in path planning in larger scenarios, the improved A* algorithm can significantly improve the path-finding speed and reduce computing power while ensuring the generation of the most efficient path, especially in larger path planning scenarios. For the threshold-sensitive characteristics of the traditional VFH algorithm, an adaptive sector threshold function is designed. By dividing obstacles into different priorities, as many obstacle avoidance paths as possible are found, ensuring the smoothness of the obstacle avoidance path, and solving the problem that the thresholds of different environments of the traditional VFH algorithm cannot be shared. In view of the defect that the traditional VFH algorithm is prone to fall into a local dead loop, the traditional cost function is improved. By predicting the signs that the unmanned ship will fall into a local dead loop in advance, the priority of obstacle avoidance direction selection is changed to ensure that when the unmanned ship falls into a dead loop, it can avoid collisions with obstacles and jump out of the local dead loop to find a path to the target point. In the path tracking stage, based on the update of the water environment model, a local path for obstacle avoidance is formulated for the unmanned ship, and then the best navigation route is formulated for the unmanned ship. At the same time, in view of the shortcomings of the current guidance law, such as complex rules, difficult parameter calibration, and narrow application, the LOS line of sight controller is improved on the basis of the PID control principle. Integral and differential terms are added to the conventional LOS guidance law. On the basis of keeping the structure of the LOS guidance law simple, pre-steering control and speed control optimization are added, which has a good control effect on the differential unmanned ship. Compared with the traditional LOS guidance law, the improved LOS guidance law has improved control error, stability and anti-interference, and improved the fast convergence performance, thereby controlling the unmanned ship to complete the path tracking function, realizing the autonomous navigation of the unmanned ship, and effectively improving the intelligence of the unmanned ship.

[0135] Any example of the present invention can be used as an independent technical solution or combined with other examples. All patents and publications mentioned in the specification of the present invention indicate that these are public technologies in the field and can be used in the present invention. All patents and publications cited here are also listed in the references, just like each publication is specifically cited separately. The present invention here can be implemented in the absence of any element or elements, one limitation or multiple limitations, and this limitation is not specifically stated here. The terms and expressions used here are descriptive methods, but not limited by them. There is no intention to indicate that these terms and explanations described in this book exclude any equivalent features, but it can be known that any appropriate changes or modifications can be made within the scope of the present invention and the claims. It can be understood that the embodiments described in the present invention are embodiments and features in some embodiments, and any person skilled in the art can make some changes and variations based on the essence of the present invention, and these changes and variations are also considered to belong to the scope of the present invention and the scope limited by the independent claims and the appended claims.

Claims

1. A remote control method for an unmanned ship, characterized in that: The following steps are involved: S1. The unmanned boat starts after passing the self-inspection; S2, obtain the spatiotemporal data T of the unmanned ship at the current moment, and send it to the shore-based ground station command system through the 5G network communication module; S3, set the target node g and the return point H for the unmanned ship on the shore-based ground station command system, set the control decision mode through the control decision module, and send it to the unmanned ship through the 5G network communication module; S4. After receiving the data from the shore-based ground station command system, the intelligent navigation module obtains the spatiotemporal data of the unmanned ship at the next moment T+1, and uses the offline electronic chart data to build and update the water environment model based on the fusion of the data obtained by the sensor module; S5. Perform path planning between the ship position and the target node g in the spatiotemporal data T+1 of the next moment of the unmanned ship, and formulate the best navigation route for the unmanned ship, specifically: The improved A* algorithm is used for global path planning. Specifically, the A* algorithm is optimized by combining the jump point search algorithm. In the path finding process, the A* algorithm uses jump points to replace a large number of unnecessary nodes in the A* algorithm, and expands by screening jump points until the final path is generated. The improved VFH algorithm is used for local path planning, specifically: adaptive sector threshold optimization is performed, the passable sectors of the unmanned ship are screened by setting appropriate thresholds, obstacles are divided into different priorities through obstacle information detected by the sensor module, and adaptive thresholds are calculated to set different thresholds for different obstacles; Perform infinite loop optimization of the improved cost function. By predicting infinite loops of all candidate directions, use different cost functions for different candidate directions to select the optimal obstacle avoidance direction. S6. After obtaining the best navigation route calculated by the intelligent navigation module, the motion control module uses the PID control method to realize the motion control of the unmanned ship on the basis of improving the LOS line of sight guidance. By optimizing the heading control and speed control, the path of the unmanned ship is tracked to realize the control of the autonomous navigation of the unmanned ship. S7. Calculate the safe distance of the ship based on the real-time scanning information of the laser radar. If the other ship and the own ship maintain a safe distance or the waters are passable, the own ship continues to sail along the original route; when the distance between the other ship and the own ship is less than the safe distance or the waters are impassable, the intelligent navigation module formulates an obstacle avoidance route and hands it over to the motion control module for immediate execution; if the obstacle avoidance route cannot be formulated in time, the emergency obstacle avoidance function will be triggered, and the vehicle will brake or move in the opposite direction immediately for emergency avoidance; the shore-based ground station command system can take over the control authority of the unmanned ship in an emergency, and the unmanned ship will be controlled manually to complete the avoidance action; S8, 5G network communication module is used to keep the unmanned ship connected to the shore-based ground station command system over a long distance, and send the unmanned ship's spatiotemporal data T to the shore-based ground station command system at a certain frequency. The shore-based ground station command system monitors the navigation status of the unmanned ship in real time; In S5, the improved VFH algorithm is used to optimize the adaptive sector threshold in local path planning as follows: M i =λ1·M max +λ2·M min In the formula, λ1·M max is the target priority, λ2·M min Safety is a priority, and M min <M max , M i is the adaptive threshold of the i-th sector, M max and M min The value range is: M L >M≥M D , M L Indicates the threshold value of the maximum scanning distance of the dangerous distance radar, M D It indicates the safe distance threshold for avoiding obstacles, and M is the safe distance that can be screened; In S5, the improved VFH algorithm is used to perform the dead loop optimization of the improved cost function in local path planning as follows: For candidate directions that are not in danger of falling into an infinite loop, set the following cost function: G=μ1△(c i ,k t )+μ2△(c i ,k n )+μ3△(c i ,g c ) For candidate directions that are in danger of falling into an infinite loop, the following cost function is set: G'=μ1△(c i ,k n )+μ2△(c i ,g c ) In the formula, μ1, μ2, μ3 represent constants, c i represents the candidate direction, k t Indicates the current heading of the unmanned ship, k n represents the last heading of the unmanned ship, g c Indicates the last heading of the unmanned ship.

2. The remote control method of an unmanned ship according to claim 1, characterized in that: The specific steps of using the improved A* algorithm to perform global path planning in S5 are as follows: S51. In the map grid, add the starting node s to OpenList, f(s) = h(s), ClosedList is used to save the nodes that have been searched, f(s) is the cost function of the A* algorithm, which represents the cost of reaching the target node g from the starting point s via any node n, and h(s) represents the heuristic function of the A* algorithm, which represents the estimated cost from node n to the target node g; S52, if OpenList is empty, the path finding fails and ends, otherwise enter S53; S53, calculate the node with the smallest f(s) value in OpenList, delete the node from OpenList, and add it to ClosedList; S54, if the current node is the target node g, the path finding is successful and ends, otherwise enter S55; S55, according to the direction of the target node g, expand in the horizontal and vertical directions, and if an obstacle is encountered or the map boundary is reached, expand in the diagonal direction; S56. If a jump point is detected, the jump point is added to the OpenList and S53 to S56 are looped. If no jump point is detected, the node is ignored and S55 to S56 are looped.

3. The remote control method of an unmanned ship according to claim 1, characterized in that: The S6 is specifically: Use PID control method to control the speed of unmanned boat: The PID control method is used to control the heading of the unmanned ship: The control system formula of the unmanned ship is obtained: In the formula, e v (t) is the difference between the actual speed and the target speed, e v (t-1) is the difference between the last calculation time and P v (t) is the output value of speed control, K p is the proportional gain in the PID controller, K d is the differential gain in the PID controller, e a (t) is the difference between the actual heading and the target heading, ω is the heading angular velocity obtained after filtering and noise reduction of the measured angular velocity, F x is the longitudinal thrust of the unmanned ship, F l 、F r is the thrust generated by the left and right motors of the unmanned ship, F d is the lateral resistance of the unmanned ship during movement, M d represents the moment on the unmanned ship, l o is the distance between the two propellers of the unmanned ship, H represents the comprehensive lateral force of the unmanned ship, and the speeds of the two motors are n l and n r .

4. The remote control method of an unmanned ship according to claim 1, characterized in that: The spatiotemporal data T of the unmanned ship in S2 includes: the current navigation positioning information of the unmanned ship, the hull posture information of the unmanned ship, the depth of field information of the water environment where the unmanned ship is located, the laser radar scanning information, the battery information, and the image information of the water environment where the unmanned ship is located.

5. The remote control method of an unmanned ship according to claim 1, characterized in that: The water environment model construction in S4 is specifically as follows: by acquiring the spatiotemporal data of the unmanned ship, fusing it with the data acquired by the sensor module, and combining it with the offline electronic nautical chart, a water environment map is constructed, the area where the unmanned ship is located is divided into a number of grids, and a grid map is created using the grid method.

6. An unmanned ship remote control system, executing an unmanned ship remote control method according to any one of claims 1 to 5, characterized in that: It includes the shore-based ground station command system and the ship-side system. The shore-based ground station command system is used for unmanned ship mission dispatching, unmanned ship status monitoring and manual control. The ship-side system includes: The 5G communication module is used to realize long-distance cross-end communication between the unmanned ship and the shore-based ground station command system, and to achieve long-distance task distribution of the unmanned ship and ship-side data reception; The control decision module is used to control the unmanned ship to achieve different control modes, including autonomous navigation mode, manual control mode, and emergency obstacle avoidance mode; The intelligent navigation module includes a sensor module, an electronic nautical chart, and a path planning module. The sensor module is used to collect the spatiotemporal data of the unmanned ship at the current moment and update the water environment model; the electronic nautical chart is used to provide accurate basic environmental data for the autonomous navigation of the unmanned ship and to build the initial water environment model; the path planning module uses the improved A* algorithm to replace unnecessary nodes in the A* algorithm with jump points, and implements global path planning by screening jump points and expanding until the final path is generated. The improved VFH path planning algorithm is used to implement local path planning through adaptive sector threshold optimization and improved cost function dead loop optimization, and the route obtained by path planning is smoothed to provide a smoother route for the unmanned ship; The motion control module realizes the motion control of the unmanned ship through the PID control method based on the path obtained by the intelligent navigation module and on the basis of improving the LOS line of sight guidance; The energy power module is used to provide power for the unmanned ship and provide battery information for decision-making on whether the mission can be completed normally.

7. An unmanned ship remote control device, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the unmanned ship remote control method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which, when called, are used to execute an unmanned ship remote control method as described in any one of claims 1-5.

Images