Intelligent unmanned ship adaptive communication control system based on dual-mode heterogeneous network

Abstract

The invention relates to the technical field of unmanned ship communication, and provides an intelligent unmanned ship adaptive communication control system based on a dual-mode heterogeneous network, which comprises a control unit, an operation unit, a communication unit and a monitoring display unit, and is characterized in that the operation unit and the monitoring display unit are respectively in direct communication connection with the control unit; the control unit is in communication connection with the unmanned ship through the communication unit, and the monitoring display unit receives and displays state data through the control unit; the communication unit comprises a first public network communication module and a first private network communication module, the first public network communication module performs data interaction with a second public network communication module of the unmanned ship at the cloud, and the first private network communication module performs bridging communication with a private network communication device of the unmanned ship. The system has the advantages of being high in integration level, high in reconfigurability, reasonable in link redundancy design and the like, the reliability and adaptability of the system in a complex electromagnetic environment and a remote operation scene are remarkably improved, and the system is suitable for an unmanned surface vessel command and control platform under variable tasks.

Description

Technical Field

[0001] This invention relates to the field of unmanned surface vessel (USV) communication technology, and in particular to an intelligent USV adaptive communication control system based on a dual-mode heterogeneous network. Background Technology

[0002] Communication quality and the speed of parsing data and generating control signals are crucial for controlling unmanned surface vessels (USVs). With the development of USV technology, USVs have been widely used in water patrol, environmental monitoring, maritime rescue, and marine mapping. However, communication technology for remotely controlling USVs still faces many challenges, especially in complex environments such as at sea and on lakes, where traditional remote control methods struggle to meet the demands of USVs for stability, low latency, and high-precision control.

[0003] Traditional wireless remote controllers mostly rely on a single communication method, such as short-range 2.4GHz wireless signals or Wi-Fi connections. In open water or long-distance environments, the signal is easily interfered with or lost, leading to loss of control of the unmanned surface vessel (USV). In the field of USV remote control, existing wireless remote control technologies suffer from problems such as unstable communication, weak long-distance control capabilities, high data transmission latency, and poor anti-interference capabilities in complex water environments, seriously affecting the safety and control accuracy of USVs. Therefore, a new communication and control system for USVs is needed to solve the technical problem of unstable communication. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent unmanned surface vessel (USV) adaptive communication control system based on a dual-mode heterogeneous network, which aims to solve the technical problem of unstable communication in existing USV communication control systems.

[0005] This application provides an intelligent unmanned surface vessel (USV) adaptive communication control system based on a dual-mode heterogeneous network, including a control unit, an operation unit, a communication unit, and a monitoring and display unit. The operation unit is used for inputting operation signals, and the operation unit and the monitoring and display unit are directly communicatively connected to the control unit. The control unit is wirelessly connected to the USV through the communication unit, and is used to convert the operation signals into control commands and send them to the USV, as well as to receive the USV's status data. The monitoring and display unit receives and displays the status data through the control unit. The communication unit includes a first public network communication module and a first private network communication module. The first public network communication module is used to interact with the second public network communication module of the unmanned surface vessel in the cloud. The first private network communication module is used to bridge communication with the private network communication device of the unmanned surface vessel. The control unit selectively switches the communication connection between the first public network communication module and the first private network communication module and the unmanned surface vessel.

[0006] In one embodiment, the control unit includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a communication adaptive handover algorithm. The communication adaptive handover algorithm includes the following steps: S100: Determine whether one of the first public network communication module and the first private network communication module is connected to the unmanned surface vessel.

[0007] S200: If so, maintain the current communication state; otherwise, start recording the time the communication was disconnected.

[0008] S300: The communication disconnection time is within a first preset time period, during which the current communication status is detected to ensure that the communication remains disconnected.

[0009] S400: If so, switch the communication connection between the first public network communication module and the first private network communication module and the unmanned surface vessel; otherwise, reset the communication disconnection time to zero.

[0010] In one embodiment, the control unit uses a counter to record the time when communication is disconnected.

[0011] In one embodiment, the first preset time is 0.5s to 1.5s.

[0012] In one embodiment, the maximum communication distance of the first public network communication module is greater than the maximum communication distance of the first private network communication module.

[0013] In one embodiment, the first public network communication module is a 3G module, a 4G module, a 5G module, a satellite communication module, a narrowband Internet of Things module, or an enhanced machine-type communication module.

[0014] In one embodiment, the first private network communication module is a WiFi module, a Bluetooth Mesh module, a microwave point-to-point communication module, or a wireless data transmission module.

[0015] In one embodiment, the operating unit includes a knob for signal input of changes in the rudder angle of the unmanned surface vessel.

[0016] In one embodiment, the operating unit includes a joystick for inputting a signal for the throttle output of the unmanned surface vessel.

[0017] In one embodiment, the operating unit includes buttons for signal input to ignite, stop, or shut down the unmanned surface vessel.

[0018] In one embodiment, the button is directly connected to the control unit via TTL level communication; and / or, the joystick and the knob are directly connected to the control unit via RS232 serial port.

[0019] In one embodiment, the status data includes the latitude and longitude, heading angle, speed, battery level, and throttle information of the unmanned surface vessel (USV); the monitoring and display unit includes a serial port screen, which is used to display the status data transmitted back by the USV in real time; the serial port screen is directly connected to the control unit via a serial port interface.

[0020] In one embodiment, the control unit sends the control command to the communication unit via a TTL serial data interface.

[0021] In one embodiment, the control unit includes an FPGA core processing board.

[0022] The beneficial effects of the intelligent unmanned surface vessel (USV) adaptive communication control system based on a dual-mode heterogeneous network provided by this invention are as follows: The control unit wirelessly connects with the USV through a communication unit to acquire the USV's status data, which is then displayed through a monitoring and display unit, providing an intuitive status display. Operators can input operation signals on the operation unit based on the status data through precise physical manipulation, improving the user experience. The control unit quickly converts the operation signals into control commands and sends them to the USV through the communication unit, enabling remote control of the USV. The communication unit includes a first public network communication module and a first private network communication module. The first public network communication module has a wide coverage and stable signal, suitable for long-distance USV control. The first private network communication module is bridged to a private network communication device, possessing high speed and low latency characteristics, suitable for short-distance control. The combination of the two modules enables adaptive switching, improving communication stability and continuity, ensuring reliable operation of the USV in harsh communication environments, meeting remote control requirements, solving the technical problem of unstable communication in existing USV communication control systems, enhancing the stability and reliability of remote control, and ensuring the safe and efficient execution of tasks by the USV. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A schematic diagram illustrating the principle of the intelligent unmanned surface vessel adaptive communication control system provided in an embodiment of the present invention; Figure 2 A schematic diagram illustrating the communication between the communication unit and the unmanned surface vessel provided in this embodiment; Figure 3 This is a flowchart illustrating the communication adaptive switching algorithm provided in the embodiment.

[0025] The following are the labeling elements in the figure: 1. Unmanned surface vessel; 10. Control unit; 20. Operating unit; 21. Knob; 22. Joystick; 23. Button; 30. Communication unit; 31. First public network communication module; 32. First private network communication module; 40. Monitoring and display unit; 41. Serial port screen. Detailed Implementation

[0026] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0027] Throughout this specification, references to "an embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of this application. Therefore, the phrases "in one embodiment" or "in some embodiments" appear in various places throughout the specification, and not all refer to the same embodiment. Furthermore, in one or more embodiments, particular features, structures, or characteristics may be combined in any suitable manner.

[0028] In the description of this invention, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0029] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0030] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0031] Combination Figure 1 This application provides an intelligent unmanned surface vessel (USV) adaptive communication control system based on a dual-mode heterogeneous network, including a control unit 10, an operation unit 20, a communication unit 30, and a monitoring and display unit 40. The operation unit 20 is used for inputting operation signals, and both the operation unit 20 and the monitoring and display unit 40 are directly communicatively connected to the control unit 10. The control unit 10 is wirelessly connected to the USV 1 via the communication unit 30, and is used to convert operation signals into control commands and send them to the USV 1, as well as to receive status data from the USV 1. The monitoring and display unit 40 receives and displays status data through the control unit 10.

[0032] Combination Figure 2 The communication unit 30 includes a first public network communication module 31 and a first private network communication module 32, meaning the communication unit 30 has two communication modes: a public network communication mode and a private network communication mode. The first public network communication module 31 and the first private network communication module 32 interact with the communication module at the end of the unmanned surface vessel 1 through bridging or switching. The first public network communication module 31 is used to interact with the second public network communication module of the unmanned surface vessel 1 in the cloud. Specifically, the first public network communication module 31 implements a public network remote data link based on a cellular network, adapting to long-distance and wide-area communication needs. The first private network communication module 32 is used for bridging communication with the private network communication equipment of the unmanned surface vessel 1. Specifically, the first private network communication module 32 is bridged with dedicated communication equipment to build a high-bandwidth, low-latency private network communication channel. The control unit 10 selectively switches the communication connection between the first public network communication module 31 and the first private network communication module 32 and the unmanned surface vessel 1.

[0033] The control unit 10 wirelessly connects to the unmanned surface vessel 1 via the communication unit 30, acquires the status data of the unmanned surface vessel 1, and displays it through the monitoring and display unit 40, providing an intuitive status display. Based on the status data, the operator can input operation signals on the operation unit 20 through precise physical control, improving the user experience. The control unit 10 quickly converts the operation signals into control commands and sends them to the unmanned surface vessel 1 via the communication unit 30, realizing remote control of the unmanned surface vessel 1. The communication unit 30 includes a first public network communication module 31 and a first private network communication module 32. The first public network communication module 31 has a wide coverage and stable signal, suitable for long-distance control of the unmanned surface vessel 1. The first private network communication module 32 is bridged to a private network communication device, possessing high speed and low latency characteristics, suitable for short-distance control. The combination of the two modules enables adaptive switching, improving communication stability and continuity, ensuring reliable operation of the unmanned surface vessel 1 in harsh communication environments, meeting remote control requirements, solving the technical problem of unstable communication in existing unmanned surface vessel 1 communication control systems, enhancing the stability and reliability of remote control, and ensuring that the unmanned surface vessel 1 can perform tasks safely and efficiently.

[0034] In some embodiments, the control unit 10 includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a communication adaptive switching algorithm.

[0035] Combination Figure 3 The above-mentioned adaptive communication handover algorithm includes the following steps: S100: Determine whether one of the first public network communication module 31 and the first private network communication module 32 is connected to the unmanned surface vessel 1.

[0036] S200: If so, maintain the current communication state; specifically, return to step S100 until the original communication connection mode is broken. Otherwise, start recording the communication disconnection time.

[0037] S300: The communication disconnection time is within a first preset time. It checks whether the current communication status remains disconnected. For example, if the first private network communication module 32 is interrupted for 500ms due to wave obstruction, the algorithm will not trigger a switch. Instead, it will reset the communication disconnection time to zero after the signal is restored, filtering out false disconnections and avoiding back-and-forth switching of communication modes to ensure a stable communication link.

[0038] S400: If so, switch the communication connection between the first public network communication module 31 and the first private network communication module 32 and the unmanned surface vessel 1; otherwise, reset the communication disconnection time to zero and maintain the current communication connection mode. Compared to immediately switching the communication mode as soon as the communication connection is broken, this algorithm avoids frequent erroneous switching, ensuring communication continuity within a first preset time and avoiding link jitter. For example, a 100ms momentary disconnection caused by maritime electromagnetic interference would erroneously switch modules. Only when the current communication mode is disconnected for more than the first preset time will the communication mode be switched, and the state will be maintained directly within the first preset time without any switching operation, reducing the brief communication gaps during the switching process.

[0039] Based on this, the system utilizes an adaptive switching algorithm to achieve adaptive switching between the first public network communication module 31 and the first private network communication module 32, overcoming the bottleneck of a single network, ensuring stable communication, adapting to complex aquatic scenarios, and making the switching strategy more aligned with actual needs. Communication signals in scenarios such as sea and lakes are often affected by numerous instantaneous interferences and complex reasons for disconnection; the algorithm's design is more suitable for these actual environments. The entire process is automatically executed by the processor without manual intervention. The processor does not require a large amount of computing power during execution and can simultaneously handle other core tasks such as operation signal parsing and status data processing.

[0040] The unmanned surface vessel (USV) is equipped with a second public network communication module and a private network communication device. It automatically selects the optimal communication path through a program and transmits received control signals to the onboard data processing center for command parsing and action execution. Simultaneously, status information collected by onboard sensors is also fed back through the same path for real-time graphical display on the monitoring display unit 40, facilitating operator decision-making and intervention.

[0041] Specifically, before step S100, the following steps are also included: When operating at sea, if the system detects whether the public network signal meets the preset qualification requirements, it will activate the first public network communication module 31 to communicate with the unmanned surface vessel 1. For example, the first public network communication module 31 will upload control commands to the cloud transparent transmission platform via the cellular network, and then the cloud will forward them to the second public network communication module on the unmanned surface vessel 1 to complete the data transmission.

[0042] Otherwise, the system automatically switches to the first private network communication module 32 to establish point-to-point or point-to-multipoint communication with the unmanned surface vessel 1 through the private network communication equipment, so as to realize the fast and reliable transmission of control commands.

[0043] Based on this, the communication link is matched with the optimal solution of the current scenario at the initial stage of the operation, while reducing unnecessary switching losses and reducing one unnecessary switching operation. For example, there will be a communication gap of 50-100ms for each switching, which allows control commands to reach the unmanned surface vessel 1 more quickly. This is especially suitable when the operation starts, as the unmanned surface vessel 1 needs to adjust its course as soon as it is launched.

[0044] Specifically, the preset qualification requirements refer to a public network signal RSRP ≥ -105dBm and a packet loss rate < 5%, indicating that the unmanned surface vessel 1 is in the open sea (e.g., 10-50km away). In this case, the first public network communication module 31 is activated first, relying on its wide-area coverage characteristics, without relying on private network equipment (such as shore-based WiFi APs), and remote control is achieved directly through cloud transmission. Here, RSRP refers to Reference Signal Received Power. If the public network signal is unqualified, such as a weak signal or frequent disconnections, it indicates that the unmanned surface vessel 1 is mostly in the near shore. Near the shore, there are often tall buildings / islands blocking the public network signal. In this case, the first private network communication module 32 is automatically switched, and low-latency transmission is achieved through private network bridging to meet the low-latency, high-bandwidth requirements for near-shore obstacle avoidance and accurate docking. If the wrong communication mode is initially selected, not only must it be switched, but invalid modules must also be shut down (e.g., if there is no private network signal in the open sea, but the first private network communication module 32 is continuously activated, resulting in wasted power), to avoid disconnection upon startup.

[0045] In one embodiment, the control unit 10 uses a counter to record the communication disconnection time. The counter can accurately time the communication disconnection through hardware or software, avoiding misjudgments caused by time errors. The counter can be directly built using logic units (such as flip-flops or adders) without calling complex operating system time functions, and does not affect the real-time processing of core tasks (such as rudder angle command generation) by the control unit 10. The counter can be reset through a simple clearing operation (such as `count=0`), preparing for the next disconnection judgment.

[0046] In one embodiment, the first preset time is 0.5s to 1.5s. Maritime communication is susceptible to momentary interference such as wave obstruction of antennas, radar sweeps from fishing boats, and electromagnetic pulses, typically lasting 0.1s to 0.3s. This time range effectively eliminates such false disconnections and prevents communication modes from switching back and forth between public and private networks. Disconnection exceeding 1.5s directly leads to the risk of loss of control (e.g., for an unmanned surface vessel 1 traveling at 10m / s, a 1.5s disconnection would cause it to drift 15m). If the disconnection exceeds 1.5s, the unmanned surface vessel 1 may have deviated from its course or approached obstacles. For example, during near-shore obstacle avoidance, if the 4G connection is lost and it takes 3 seconds to switch to WiFi, the unmanned surface vessel 1 may not receive obstacle avoidance commands during this period, making it prone to colliding with the dock. The communication mode switching is completed within a maximum of 1.5s. Even if the unmanned surface vessel 1 is traveling at 5m / s, the disconnection interval only results in a drift of 7.5m, and control can be quickly restored after the switch, which is sufficient to meet the safety requirements of most maritime operations (e.g., low-speed cruising in the open sea and medium-speed obstacle avoidance near the shore).

[0047] Specifically, the first preset time is 0.5s, 0.8s, 1.0s, 1.2s or 1.5s.

[0048] In some embodiments, the maximum communication distance of the first public network communication module 31 is greater than the maximum communication distance of the first private network communication module 32.

[0049] In some embodiments, the first public network communication module 31 includes at least one of a 3G module, a 4G module, a 5G module, a satellite communication module, a narrowband IoT module, and an enhanced machine-type communication module. The 3G module is suitable for basic communication in remote near-shore areas (areas with sparse base stations), the 4G module balances coverage and bandwidth (supporting 10-50km control commands + medium data backhaul), and the 5G module (especially in the Sub-6GHz band) provides low latency (<50ms) and high bandwidth (100Mbps+), suitable for near-shore high-definition video transmission and precise control (such as port operations and obstacle avoidance in narrow waterways). For long-distance / ultra-long-distance (50-500km) communication, satellite communication modules (such as Iridium and BeiDou short message services) are used, eliminating the need for ground base stations and achieving full coverage via satellite. Even in areas without terrestrial networks, such as the open ocean and polar regions, critical commands (such as return trips and fault alarms) and low-frequency status data (such as latitude, longitude, and battery level) can still be transmitted. Narrowband IoT modules and enhanced machine communication modules are low-power wide-area networks (LPWAN) for operators, with coverage comparable to 4G modules (relying on existing base stations), but power consumption is only 1 / 10 of 4G. They are suitable for long-term unmanned surface vessels (USVs) for tasks such as lake water quality monitoring, and can be kept up for months without charging, continuously transmitting small amounts of data (such as water quality parameters once a week).

[0050] In some embodiments, the first private network communication module 32 includes at least one of a WiFi module, a Bluetooth Mesh module, a microwave point-to-point communication module, and a wireless data transmission module. The microwave point-to-point communication module (such as the NexFi MB series) transmits data at line of sight, reaching a maximum distance of 30 kilometers in unobstructed environments, with a bandwidth of up to 80 Mbps. It can replace the public network to achieve high-definition video transmission and real-time control command issuance between the port and the unmanned surface vessel 1, with a latency of less than 10 ms. The WiFi module uses LR-WiFi technology, supporting low-latency (<50 ms) and interference-resistant (frequency hopping + filtering) data transmission within 8 kilometers, suitable for precise control in near-shore operations (such as port obstacle avoidance and cargo hoisting). The Bluetooth Mesh module supports multi-node self-organizing networks, with a single-hop transmission distance of up to 200 meters (in open outdoor environments). It can connect sensors, cameras, and actuators in the unmanned surface vessel 1 formation to achieve low-power (standby current <1mA) and highly robust state synchronization between devices.

[0051] Specifically, when the first private network communication module 32 is a WiFi module, the WiFi module transmits data via a 2.4GHz / 5GHz carrier wave. Environmental interference (such as near-shore obstacles and low-frequency noise from industrial equipment) is mostly concentrated in lower frequency bands (or spurious signals in the same frequency band), requiring precise stripping through multi-scale coding. The memory of the control unit 10 stores the following complex STFT frequency domain separation algorithm, which performs complex STFT processing on the raw IQ signal received by the WiFi, setting the following dual-window function: F intf (t,f)=ComplexReLU(STFT C (x WiFi W low )) F data (t,f)=ComplexReLU(STFT C (x WiFi W high ))

[0052] Where t is time, f is frequency, and W low Corresponds to the 0~100kHz low frequency band; W high Compatible with 2.4GHz or 5GHz WiFi operating frequency bands; F intf (t,f) represents the separated low-frequency interference characteristics, such as the 50Hz harmonics of low-frequency noise from near-shore obstacles and industrial equipment; F data (t,f) represents high-frequency useful data characteristics, such as the OFDM subcarrier signal of WiFi. The first formula is derived through W... low The low-frequency components (interference) in the WiFi signal are filtered out, then converted into time-frequency domain interference features using STFTC, and finally ComplexReLU is used to suppress invalid noise, outputting a "time-frequency domain interference feature map". Interference cancellation algorithms can be designed based on this map. The second formula is obtained through W... high High-frequency components (useful data) in the WiFi signal are filtered out, then converted into time-frequency domain data features by STFTC, and finally the effective data is retained by ComplexReLU, outputting a "time-frequency domain useful data feature map". Based on this map, data demodulation is performed (recovering binary 0 / 1).

[0053] The complex STFT frequency domain separation algorithm improves the interference rejection ratio (SIR) by 15-20dB, enhances the signal-to-noise ratio (SNR) of the separated WiFi useful signal, and reduces the bit error rate from 10. -3 Reduced to 10 -5 On the other hand, multipath tolerance is enhanced. In near-shore multi-reflection environments (such as ports), the packet loss rate of WiFi is reduced from 20% to below 5%, without relying on additional anti-multipath algorithms (such as OFDM symbol extension).

[0054] In some embodiments, the unmanned surface vessel 1 has an electromagnetic sensor for detecting the intensity of electromagnetic interference. Based on the intensity of electromagnetic interference, the control unit 10 adjusts the radio frequency power of the communication power supply or adjusts the signal modulation method to reduce the impact of interference on data transmission. Specifically, if the intensity of electromagnetic interference in the environment is high, a fixed radio frequency power may cause transmission interruptions (such as data packet loss) or errors (such as bit flipping) due to signal interference, resulting in data transmission failure. By sensing the intensity of electromagnetic interference in real time and adjusting the power, when the interference is strong, the radio frequency power is automatically increased to enhance the signal's anti-interference capability and ensure complete data transmission; when the interference is weak, low-power transmission is maintained to reduce the possibility of data being illegally intercepted at the transmission level.

[0055] In some embodiments, combined with Figure 1 The operating unit 20 includes a knob 21, which is used as a signal input for the change of the rudder angle of the unmanned surface vessel 1. The rotation angle of the knob 21 (e.g., 0°~180°) can establish a linear correspondence with the change in rudder angle (e.g., 0°~30°) (e.g., for every 6° rotation of the knob 21, the rudder angle is adjusted by 1°). By controlling the rotation amplitude, the operator can precisely control the magnitude of the change in rudder angle.

[0056] In some embodiments, combined with Figure 1 The operating unit 20 includes a joystick 22, which is used as the signal input for the throttle output of the unmanned surface vessel 1. The travel of the joystick 22 (such as the distance it is pushed forward or backward) can establish a linear correspondence with the throttle percentage (for example, pushing the joystick 22 to its maximum travel corresponds to 100% throttle, and pushing it to 1 / 2 travel corresponds to 50% throttle). By controlling the pushing amplitude, the operator can precisely control the throttle increment (such as fine-tuning the throttle by 5% to avoid slower boats, or pushing it to 80% throttle to accelerate the return trip). When the operator pushes the joystick 22, they can sense the current throttle level through the tactile resistance, without having to look down at the screen, allowing them to focus on observing the surrounding environment. The analog signal (such as a 0-5V voltage signal) or digital signal (such as an RS232 protocol) of the joystick 22 is not easily affected by electromagnetic interference at sea (such as radar on fishing boats). Compared with wireless signals (such as Bluetooth throttle controllers), the signal loss rate is almost zero, ensuring uninterrupted throttle control.

[0057] In one embodiment, combined Figure 1The joystick 22 and knob 21 are directly connected to the control unit 10 via an RS232 serial port. The RS232 serial port is an asynchronous serial communication protocol with a simple protocol (no complex handshake process) and extremely low data transmission latency (typically <10ms), ensuring that the operation signals of the joystick 22 (throttle) and knob 21 (rudder angle) are sent and received immediately. For example, when the operator pushes the joystick 22 to adjust the throttle (e.g., from 30% to 50%) or rotates the knob 21 to adjust the rudder angle (e.g., from 0° to 10°), the RS232 serial port can directly transmit analog (or digital) signals to the control unit 10 without requiring protocol conversion (e.g., encryption / decryption in wireless communication) or intermediate forwarding devices. The signal transmission link is short, and the latency is more than 50% lower than that of wireless communication (e.g., Bluetooth latency of 20-50ms).

[0058] In some embodiments, combined with Figure 1 The operating unit 20 includes buttons 23, which are used for signal input to ignite, stop, or shut down the unmanned surface vessel 1. Specifically, there are multiple buttons 23, each corresponding to a specific signal input. The direct triggering characteristic of the buttons 23 allows commands to be issued immediately upon pressing, with a response speed much faster than input devices that require adjustment. For example, when the unmanned surface vessel 1 suddenly encounters a reef or an oncoming ship, the operator presses the stop button, and the signal can be directly transmitted to the control unit 10 (delay <10ms), and the control unit 10 immediately generates a power cut-off command.

[0059] In one embodiment, combined Figure 1 Button 23 communicates directly with control unit 10 via TTL level. Control unit 10's GPIO interface natively supports TTL level (typically 3.3V or 5V unipolar level), eliminating the need for additional hardware conversion and simplifying system design from the ground up. TTL levels (such as low 0V and high 3.3V) can be directly recognized by control unit 10's GPIO interface. TTL level communication is a direct transmission of level signals, without complex communication protocols (such as UART start and stop bits) or data packing / unpacking processes. Button 23's operation is detected immediately upon pressing, with latency significantly lower than other communication methods.

[0060] The operating unit 20 enhances the stability and reliability of remote control, ensuring that the unmanned surface vessel 1 can perform its missions safely and efficiently.

[0061] In some embodiments, the status data includes the latitude and longitude, heading angle, speed, battery level, and throttle information of the unmanned surface vessel (USV) 1. The latitude and longitude and heading angle clearly indicate the position and direction of the USV 1. The operator can use the latitude and longitude to confirm whether the USV 1 has reached the preset monitoring point, and the heading angle to determine whether it is traveling along the planned route. The speed and throttle information match speed and power. When avoiding obstacles near the shore, the operator can use the speed to determine if the current speed is safe, and the throttle information to verify whether the power output is normal.

[0062] In one embodiment, the monitoring and display unit includes a serial port screen 41, which is used to display the status data transmitted back by the unmanned surface vessel 1 in real time. The serial port screen 41 is directly connected to the control unit 10 via a serial port interface, providing intuitive status display and precise physical control, thus improving the user experience. The control unit 10 integrates a UART serial port interface, allowing the serial port screen 41 to be directly connected without complex adaptation, significantly reducing system complexity.

[0063] In one embodiment, the control unit 10 sends control commands to the communication unit 30 via a TTL serial data interface. The UART interface of the control unit 10 (which supports TTL levels) can directly interface with the TTL serial interface of the communication unit 30, without the need for a MAX232 level conversion chip like RS232, or a USB-to-serial chip like USB. TTL serial communication has no complex protocol overhead, and the control command is sent from the control unit 10 to the communication unit 30 in only 1~2ms. Including the reception and parsing time of the communication unit 30 (<3ms), the overall delay is <5ms.

[0064] In one embodiment, the control unit 10 includes an FPGA core processing board. Combined with the high-speed data processing capabilities of the FPGA, stable, low-latency remote control is achieved.

[0065] In some embodiments, the system further includes a remote control housing, on which the control unit 10, operation unit 20, communication unit 30, and monitoring display unit 40 are fixedly mounted. To ensure communication data security and prevent unauthorized operation of the operation unit 20, the remote control housing has a hinged cover. The cover is equipped with a camera and microphone array electrically connected to the control unit 10. The cover will only open after successful authorization verification, allowing the operator to operate the operation unit 20. Specifically, the control unit 10 stores an authentication algorithm, including the following steps: S11: Input the operator's facial image and voice information into the identity verification neural network model. The facial image is captured by a camera, and the voice information is extracted from voice commands collected by a microphone array. The identity verification neural network model is a deep learning model for identity recognition, integrating facial recognition and voiceprint recognition functions, and this model is deployed in the control unit 10.

[0066] S12: For facial images, feature extraction and matching are performed using convolutional neural networks. For example, a pre-trained CNN model (such as ResNet, VGG, etc.) is used to extract facial features, which are then compared with the facial features of authorized personnel pre-stored in the system to complete the initial identity determination. Optionally, before inputting the facial image into the facial recognition model, preprocessing operations, including noise reduction, enhancement, and cropping, are required to improve recognition accuracy.

[0067] S13: For voice information, feature extraction and matching are achieved through deep learning models (such as a Transformer-based voiceprint recognition model). For example, a pre-trained voiceprint recognition model is used to extract voiceprint features from the speech, which are then compared with the voiceprint features of authorized personnel pre-stored in the system to further confirm identity. Optionally, the collected voice information needs to be pre-processed before processing, including noise reduction, enhancement, and segmentation. In this way, the verification method first collects and processes image and sound data, and then combines the identity recognition capabilities of the identity verification neural network model to achieve accurate verification of the operator's identity.

[0068] Specifically, before step S11 is executed, the authentication algorithm also includes the following process: S14: Acquire the operator's sound source location and facial position. The sound source location refers to the spatial coordinates of the operator's voice commands. This is calculated using beamforming technology or Time Difference of Arrival (TDOA) algorithms after the voice commands are acquired via a microphone array. For example, by capturing sound signals using a microphone array and analyzing the time difference of sound arrival at different microphones, the physical location of the sound source can be accurately determined. Facial position is captured by a camera or depth sensor to capture head movements, and then real-time positioning is achieved using computer vision technologies (such as OpenPose and MediaPipe frameworks). Taking camera acquisition as an example, the OpenPose algorithm identifies the coordinates of key head nodes, thereby calculating the complete head spatial position.

[0069] S15: Input the sound source location and facial location into the location verification neural network model to generate fused features. The location verification neural network model is a deep learning model used to fuse sound source location and facial location information. Specifically, it can adopt a multimodal Transformer architecture or a graph neural network (GNN). During the operation, the model first aligns the sound source location and facial location in the spatiotemporal dimensions, then completes the feature fusion, and finally generates a joint feature representation containing the two location information, i.e., the fused features.

[0070] S16: Determine whether the operator's identity conforms to the preset rules based on the fusion features. The core of the preset rules here is: the sound source position and the facial position must meet the spatial consistency. If the two spatial positions do not match, the identity verification is directly determined to be unqualified, and steps S11 to S13 do not need to be executed; if the two spatial positions match, then the verification process of steps S11 to S13 is entered.

[0071] By fusing multimodal features and performing rule verification on the location of the sound source and the facial location, this design further enhances the reliability and security of identity verification.

[0072] In summary, this invention relates to an intelligent unmanned surface vessel (USV) adaptive communication control system based on a dual-mode heterogeneous network, belonging to the field of intelligent unmanned system control. The device consists of a control unit 10, a control unit 20, a communication unit 30, and a monitoring and display unit 40. The FPGA core processing board serves as the data processing and control center, receiving inputs from the knob 21, joystick 22, and buttons 23 to achieve high-precision control of the rudder angle and throttle. The monitoring and display unit 40 uses a serial port screen 41 to analyze and display real-time position information (latitude and longitude), heading, speed, battery level, and propulsion status data transmitted back by the onboard system. The adaptive communication unit 30 integrates 4G and WIFI modules and uses a communication adaptive switching algorithm. The 4G module uses a cellular network to achieve a public network remote data link, adapting to long-distance and wide-area communication needs; the WIFI module can bridge with dedicated communication equipment to build a high-bandwidth, low-latency private network communication channel. The system has advantages such as high integration, strong reconfigurability, and reasonable link redundancy design, which significantly improves the reliability and adaptability of the remote controller in complex electromagnetic environments and remote operation scenarios. It is suitable for the command and control platform of unmanned surface vessels under various missions.

[0073] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A dual-mode heterogeneous network-based intelligent unmanned surface vehicle adaptive communication control system, characterized in that: The control unit, the operation unit, the communication unit and the monitoring display unit are included, the operation unit is used for the input of operation signal, the operation unit and the monitoring display unit are directly connected with the control unit in communication respectively; the control unit is connected with the unmanned ship in wireless communication through the communication unit, used for converting the operation signal into control instruction and sending to the unmanned ship, and used for receiving the state data of the unmanned ship; the monitoring display unit receives and displays the state data through the control unit; The communication unit includes a first public network communication module and a first private network communication module, the first public network communication module is used for data interaction with the second public network communication module of the unmanned ship in the cloud, and the first private network communication module is used for bridge communication with the private network communication equipment of the unmanned ship, and the control unit switches the first public network communication module and the first private network communication module to communicate with the unmanned ship. 2.The dual-mode heterogeneous network based intelligent unmanned surface vehicle adaptive communication control system of claim 1, wherein: The control unit includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the communication adaptive switching algorithm is realized when the processor executes the computer program; the communication adaptive switching algorithm includes the following steps: S100: whether one of the first public network communication module and the first private network communication module is connected with the unmanned ship; S200: if so, the current communication state is maintained; Otherwise, start recording the disconnection communication time; S300: the disconnection communication time is within the first preset time, and whether the current communication state is disconnected is detected; S400: if so, switch the other of the first public network communication module and the first private network communication module to communicate with the unmanned ship; Otherwise, the disconnection communication time is cleared. 3.The dual-mode heterogeneous network based intelligent unmanned surface vehicle adaptive communication control system of claim 2, wherein: The control unit uses a counter to record the disconnection communication time. 4.The dual-mode heterogeneous network based intelligent unmanned surface vehicle adaptive communication control system of claim 2, wherein: The first preset time is 0.5s~1.5s.

5. The dual-mode heterogeneous network based intelligent USV adaptive communication control system of claim 1, wherein: The maximum communication distance of the first public network communication module is greater than that of the first private network communication module. 6.The dual-mode heterogeneous network based intelligent unmanned surface vehicle adaptive communication control system of claim 1, wherein: The first public network communication module is a 3G module, a 4G module, a 5G module, a satellite communication module, a narrowband Internet of Things module or an enhanced machine type communication module; And / or, the first private network communication module is a WiFi module, a Bluetooth Mesh module, a microwave point-to-point communication module or a wireless data transmission module. 7.The dual-mode heterogeneous network based intelligent unmanned surface vehicle adaptive communication control system of claim 1, wherein: The operation unit includes a knob, which is used for the signal input of the rudder angle change of the unmanned ship; And / or, the operation unit includes a joystick, which is used for the signal input of the throttle output of the unmanned ship; And / or, the operation unit includes a key, which is used for the signal input of the ignition, stopping or extinguishing of the unmanned ship. 8.The dual-mode heterogeneous network based intelligent unmanned surface vehicle adaptive communication control system of claim 7, wherein: The key is directly connected with the control unit in communication by TTL level; and / or, the joystick and the knob are directly connected with the control unit in communication by RS232 serial port. 9.The dual-mode heterogeneous network based intelligent unmanned surface vehicle adaptive communication control system of claim 1, wherein: The state data includes longitude, latitude, heading angle, speed, power and throttle information of the unmanned ship; the monitoring display unit includes a serial port screen, which is used for real-time display of the state data returned by the unmanned ship; and the serial port screen is directly connected with the control unit through a serial port interface.

10. The dual-mode heterogeneous network based intelligent unmanned surface vehicle adaptive communication control system according to any one of claims 1 to 9, characterized in that: The control unit sends the control instructions to the communication unit through a TTL serial data interface; and the control unit includes an FPGA core processing board.

Images