11
2024-06-11
Ocean Forum | Adaptive Heading Control Research of the “Black Pearl” Unmanned Surface Vehicle
Summary:
1. Introduction
With the development of the global economy and the continuous growth of population, energy shortages and environmental pollution have become increasingly severe. As a result, greater attention is being directed toward the oceans, which cover approximately 71% of the Earth’s surface. In order to support marine resource exploration, climate research, marine disaster early warning, and maritime rights protection, large-scale, long-duration, and systematic ocean observations are required. Consequently, the global demand for marine observation technologies is increasing rapidly.
As an emerging unmanned mobile ocean observation platform, the Unmanned Surface Vehicle converts wave energy into forward propulsion. The surface platform is equipped with battery packs and solar panels to provide continuous power, enabling long-endurance offshore operations, while the submerged unit can carry various sensors and acoustic payloads. Compared with other types of unmanned marine vehicles, the Unmanned Surface Vehicle has broad application prospects in meteorological observation, environmental monitoring, and defense-related fields.
Heading control technology is a key enabler for intelligent station-keeping, autonomous navigation, and path tracking of Unmanned Surface Vehicles, and is a fundamental prerequisite for completing various marine missions. However, during operation in complex ocean environments, Unmanned Surface Vehicles are subject to significant uncertainties in system parameters. At the same time, they are affected by external disturbances such as waves, ocean currents, and wind. In addition, their time-varying nonlinear and underactuated characteristics make traditional heading control methods less effective, resulting in poor control accuracy and insufficient environmental adaptability.
To address these challenges, this study proposes a heading control method based on a BP neural network combined with an incremental PID controller. Simulation-based sea trial verification demonstrates that the proposed method significantly improves heading control accuracy and environmental adaptability.
2. Overview of the Adaptive Heading Control Method for the “Black Pearl” Unmanned Surface Vehicle
First, neural networks are a class of machine learning algorithms that adjust neuron weights based on a fitness function to adapt to changing data environments, which is consistent with the continuously varying system parameters and environmental conditions of Unmanned Surface Vehicles. Second, neural networks exhibit strong fault tolerance and robustness, meaning that the failure of a small number of neurons does not affect the overall system stability. In addition, their nonlinear mapping capability allows them to learn and store input–output relationships effectively.
As a widely used global approximation neural network, the BP (Back Propagation) neural network features a simple structure and broad applicability.
The performance of PID control depends heavily on parameter tuning. Proper adjustment of parameters according to the system structure and operating environment can significantly improve control performance. However, conventional position-based PID controllers suffer from several limitations, including high computational load, accumulated errors, susceptibility to integral windup, and instability under fault conditions. Therefore, an incremental PID approach is adopted and combined with a neural network to dynamically adjust control parameters.
Based on the above design concept, the control block diagram is shown in Figure 1.

Figure 1 Closed-Loop Heading Control Block Diagram
A BP neural network is used to approximate the uncertain parameters in the system and to tune the IPID gains, enabling dynamic optimization of the IPID parameters according to changing sea conditions and achieving high-precision heading tracking control of the Unmanned Surface Vehicle.
As shown in Fig. 2, the IPID control law is incorporated as the control layer within the parameter tuning neural network (NN1). The input layer neurons consist of the desired system output, the actual system output, the heading error, and the actual output of the rudder servo. The output layer generates the IPID gains.

Figure 2 Control Parameter Tuning Neural Network
For the unknown terms of the system, a system identification neural network (NN2) is employed for approximation. As shown in Fig. 3, NN2 takes two sets of time-series data, including rudder servo control increments and actual heading, as inputs to the input layer.
The output layer is designed to produce an estimated value of the actual heading. By identifying and predicting the nonlinear dynamic relationship between inputs and outputs, NN2 is able to approximate the system’s uncertain parameters.
By using two sets of time-series data as inputs, NN2 not only approximates the unknown parameters but also achieves a certain degree of predictive capability.

Figure 3 System Parameter Identification Neural Network
3. Simulation and Sea Trials
1. Numerical Simulation
To better simulate the motion behavior of the Unmanned Surface Vehicle at sea and further verify the effectiveness of the proposed control method in real-world environments, time-varying disturbance signals are introduced into the simulation.
The responses of different heading control methods under square-wave and sinusoidal reference signals are shown in Fig. 4.

(a) Square Wave Signal

(b) Sinusoidal Signal
Figure 4 Comparison of Heading Control Simulation Results
The proposed control method demonstrates smaller and smoother heading tracking errors, as well as shorter convergence time under different input signals. In addition, compared with conventional PID control, the NN-IPID-based heading control method results in reduced rudder angle oscillations and can effectively mitigate rudder saturation to a certain extent.
2. Sea Trials
The experimental platform is shown in Fig. 5. The surface float mainly consists of modules such as the battery compartment, main control unit, and meteorological station. The vertical rudder at the tail of the submerged glider controls its steering and drives the motion of the surface float. The umbilical cable is primarily composed of a steel cable, communication lines, and rubber materials.
The heading information of the Unmanned Surface Vehicle is obtained from an electronic compass and transmitted to the main control unit via the umbilical cable. Control commands from the main controller are also sent through the umbilical cable to the rudder servo, thereby controlling the steering of the Unmanned Surface Vehicle.

Figure 5 Experimental Platform
The results of the fixed heading tracking experiment are shown in Fig. 6, which presents a comparison of heading control performance between two Unmanned Surface Vehicles. Compared with the conventional PID method, the Unmanned Surface Vehicle using the IAJS-NN-IPID approach converges more rapidly to the desired heading with smaller oscillations.
In addition, the IAJS-NN-IPID-based Unmanned Surface Vehicle exhibits lower saturation levels and smaller amplitudes in rudder angle output, indicating improved robustness in rudder servo control.

Figure 6 Sea Trial Comparison
The path-following experimental results are shown in Fig. 7 and Fig. 8, presenting a comparison of path tracking and heading control performance between two Unmanned Surface Vehicles. Overall, the Unmanned Surface Vehicle using the IAJS-NN-IPID control method achieves smaller heading tracking errors and smoother rudder servo outputs.
Based on the actual sea trial results, the achieved heading tracking accuracy is considered satisfactory.

(a) PID Experimental Path

(b) PID Path Error and Speed

(c) PID Heading Tracking
Figure 7 PID Path Tracking

(a) IAJS-NN-PID Experimental Path

(b) IAJS-NN-IPID Path Error and Speed

(c) IAJS-NN-IPID Heading Tracking
Figure 8 IAJS-NN-IPID Path Tracking
4. Conclusions and Future Work
This paper proposes a heading control method based on a BP neural network self-tuning IPID controller. The proposed approach utilizes a neural network to tune IPID parameters and approximate unknown dynamics in the control system. By leveraging the nonlinear mapping and self-learning capabilities of the BP neural network, the IPID parameters are dynamically adjusted. Meanwhile, the global approximation capability of the BP neural network is used to estimate system uncertainties.
In addition, the IAJS algorithm is employed to optimize the initial parameters of the neural network, thereby improving the accuracy of both controller parameter tuning and system uncertainty approximation. Simulation results validate the effectiveness and feasibility of the proposed heading control method.
Furthermore, fixed heading tracking experiments and circular path-following experiments were conducted in nearshore waters of Qingdao. The experimental results demonstrate that the proposed method significantly improves the heading control accuracy of the Unmanned Surface Vehicle, exhibits stronger robustness, and ensures long-term operational reliability.
Key words:
Related News
How GNSS Positioning Solutions are Transforming Marine Surveying Techniques
How GNSS Positioning Solutions are Transforming Marine Surveying Techniques In the rapidly evolving field of marine surveying, the integration of GNSS (Global Navigation Satellite System) positioning solutions has revolutionized traditional methods of data collection and analysis. This article delves into how GNSS technology enhances precision, reliability, and safety in marine surveying, paving t
Nov 15,2026
Enhancing Deep Sea Navigation: The Role of Underwater Beacons in Positioning
The advent of underwater beacons has significantly revolutionized deep-sea positioning, a critical aspect of various marine operations, including scientific research, underwater construction, and search-and-rescue missions. These devices, often deployed to assist in locating submersible vehicles or underwater assets, utilize acoustic signals to provide real-time positioning data, which is vital fo
Nov 10,2026
A Comprehensive Guide to Selecting the Right Hydrophone Buoy for Marine Applications
A Comprehensive Guide to Selecting the Right Hydrophone Buoy for Marine Applications Table of Contents 1. Introduction to Hydrophone Buoys 2. What is a Hydrophone Buoy? 3. Importance of Hydrophone Buoys in Marine Research 4. Types of Hydrophone Buoys 5. Key Features to Consider When Selecting a Hydrophone Buoy 6. Environmental Factors Impacting Hydrophone Performance 7
Oct 21,2026
Understanding Shallow Water AIS Beacons: Enhancing Marine Safety and Navigation
Shallow water AIS beacons are specialized devices designed to aid navigation in shallow or restricted waters. AIS stands for Automatic Identification System, a vital communication tool for maritime safety that enables vessels to exchange information about their position, course, and speed in real time. These beacons serve as an important navigational aid, especially in areas where traditional navi
Oct 16,2026
Essential Marine AIS Beacon Transponder Maintenance Tips for Longevity
Essential Marine AIS Beacon Transponder Maintenance Tips for Longevity Table of Contents Understanding Marine AIS Beacon Transponders Importance of Regular Maintenance Routine Inspection Procedures Cleaning Your AIS Transponder Battery Maintenance and Replacement Software Updates and Firmware Management Troubleshooting Common Issues Professional Servicing: When to
Oct 11,2026
The Future of Wind Powered Unmanned Vessels: Revolutionizing Maritime Operations
In recent years, wind powered unmanned vessels have gained significant attention as a sustainable alternative in maritime operations. These vessels utilize wind energy as their primary propulsion source, which not only reduces reliance on fossil fuels but also minimizes greenhouse gas emissions. This environmentally conscious approach aligns perfectly with the global push for greener technologies
Oct 06,2026