Unmanned Surface Vehicles (USVs) are rapidly becoming mission-indispensable for a variety of naval operations, from search and rescue to environmental monitoring and surveillance. Path planning lies at the heart of the operational effectiveness of USVs, since it represents the key technology required to enable the vehicle to transit the unpredictable dynamics of the marine environment in an efficient and safe way. The paper develops a critical review of the most recent advances in USV path planning and a novel classification of algorithms according to operational complexity: Basic Pathfinders, Responsive Pathfinders, and Advanced Strategic Pathfinders. Each category can adapt to different requirements, from environmental predictability to the desired degree of human intervention, and from stable and controlled environments to highly dynamic and unpredictable conditions. The review includes current methodologies and points out the state-of-the-art algorithmic approaches in their experimental validations and real-time applications. Particular attention is paid to the description of experimental setups and navigational scenarios showing the realistic impact of these technologies. Moreover, this paper goes through the key, open challenges in the field and hints at the research direction to leverage in order to enhance the robustness and adaptability of path planning algorithms. This paper, by offering a critical analysis of the current state-of-the-art, lays down the foundation of future USV path planning algorithms.
Path-keeping requires unmanned surface vehicles (USVs) to follow a planned path in autonomous navigation. It is essential for USVs to carry out autonomous tasks such as collecting various data of water quality and surrounding terrain for exploration and protection of water environments. However, due to obstacle avoidance and other factors such as wind, water waves, and dynamics of USVs, USVs usually deviate from the original planned path during autonomous navigation. This paper proposes a novel path-keeping algorithm based on the artificial potential field method (PK-APF) for USVs. To minimize the deviation between the actual path and the original planned path, the vertical distance and the virtual foot points of the current position of USVs to the original path (a line connecting the previous navigation point and the next navigation point) are calculated. When the vertical distance is larger than a threshold, we regard the vertical foot point as a virtual goal point to guide the USVs to navigate the original path in real-time to achieve high-precision path-keeping. Obstacle avoidance is simulated in the MATLAB and Virtual RobotX (VRX) simulators, and the influence of wind and water waves is considered in VRX. Experiments are conducted in typical scenarios and results show that PK-APF outperforms the traditional APF by at least 22%. The work provides an important basis for real-life environments. Substantial further work is planned for applying the method on a physical USV.
The continuous advancement of autonomy and intelligence in marine shipping has made the safe and efficient navigation of unmanned surface vehicles in complex waters a major research focus. As a key link of the autonomous decision-making system for unmanned surface vehicles (USVs), local path planning needs to achieve real-time collision avoidance and motion optimization under dynamic obstacles, multiple rule constraints, and strong environmental uncertainty. In recent years, reinforcement learning has gradually become an important technical route for local path planning of USVs by virtue of its autonomous decision-making ability in high-dimensional continuous state space and adaptability to complex nonlinear problems. Combined with the evolution of the algorithm paradigm and its functional positioning in different water scenarios, this paper systematically reviews the relevant literature by examining the evolution of algorithmic paradigms; focuses on summarizing deep Q-network (DQN), Proximal Policy Optimization (PPO), Soft Actor-Critic (SAC), and Twin Delayed Deep Deterministic Policy Gradient (TD3), along with the collaborative architectures integrated with traditional planning methods such as A* and Rapidly-exploring Random Tree (RRT); and summarizes the performance characteristics, advantages, and limitations of various methods in typical scenarios. The review shows that the main bottlenecks of current research include insufficient reward mechanism design, low sample utilization efficiency, difficulty in transferring from simulation to real ships, and insufficient safety and trustworthiness verification. This paper looks forward to the future development trends from the two directions of data fusion and security enhancement in order to provide reference for related research.
20 January 2026 in IEEE Transactions on Instrumentation and Measurement
While deep learning-based robotic grasping technology has demonstrated strong adaptability, its computational complexity has also significantly increased, making it unsuitable for scenarios with high real-time requirements. Therefore, we propose a low computational complexity and high accuracy model named VMGNet for 2D planar robotic grasping. For the first time, we introduce the Visual State Space into the robotic grasping field to achieve linear computational complexity, thereby greatly reducing the model’s computational cost. Meanwhile, to improve the accuracy of the model, we propose an efficient and lightweight multi-scale feature fusion module, named Fusion Bridge Module, to extract and fuse information at different scales. We also present a new loss function calculation method to enhance the importance differences between subtasks, improving the model’s fitting ability. Experiments show that VMGNet has only 8.7G Floating Point Operations and an inference time of 8.1 ms on our devices. VMGNet also achieved state-of-the-art performance on the Cornell and Jacquard public datasets. To validate VMGNet’s effectiveness in practical applications, we conducted real grasping experiments in multi-object scenarios, and VMGNet achieved an excellent performance with a 94.4% success rate in real-world grasping tasks. The code and video for the real-world robotic grasping experiments are available at https://github.com/momo7941/VMGNet.
Autonomous path planning along riverbanks is crucial for unmanned surface vehicles (USVs) to execute specific tasks such as levee safety detection and underwater pipe inspections, which are vital for riverbank safety and water environment protection. Given the intricate shapes of riverbanks, the dynamic nature of tidal influences, and constraints in real-time cartographic updates, there is a heightened susceptibility to inaccuracies during manual waypoint designation. These factors collectively impact the efficiency of USVs in following riverbank paths. We introduce a riverbank following planner (RBFP) for USVs to tackle this challenge. This planner, utilizing 2D LiDAR, autonomously selects the following point to follow riverbank shapes. Additionally, a PID controller is integrated to compensate for position and yaw errors. Our proposed method reduces the deviation between the USV’s planned path and the actual riverbank shape. We simulated straight, convex, and concave riverbanks in the Virtual RobotX (VRX) simulator while considering the impacts of wind, waves, and USV dynamics. The experimental result indicates the following performance of 96.92%, 67.30%, and 61.15% for straight, convex, and concave banks, respectively. The proposed RBFP can support a novel autonomous navigation scenario for autonomous paths following along the riverbank without any preplanned paths or destinations.