Underwater multi-robot cooperative coverage remains challenging due to partial observability, limited communication, environmental uncertainty, and the lack of access to global localization. To address these issues, this paper presents a semantics-guided fuzzy control framework that couples Large Language Models (LLMs) with interpretable control and lightweight coordination. Raw multimodal observations are compressed by the LLM into compact, human-interpretable semantic tokens that summarize obstacles, unexplored regions, and Objects Of Interest (OOIs) under uncertain perception. A fuzzy inference system with pre-defined membership functions then maps these tokens into smooth and stable steering and gait commands, enabling reliable navigation without relying on global positioning. Then, we further coordinate multiple robots by introducing semantic communication that shares intent and local context in linguistic form, enabling agreement on who explores where while avoiding redundant revisits. Extensive simulations in unknown reef-like environments show that, under limited sensing and communication, the proposed framework achieves robust OOI-oriented navigation and cooperative coverage with improved efficiency and adaptability, narrowing the gap between semantic cognition and distributed underwater control in GPS-denied, map-free conditions.
In this paper we study the time delays affecting the diffusion of information in an underwater heterogeneous robot swarm, considering a time-sensitive environment. In many situations each member of the swarm must update its knowledge about the environment as soon as possible, thus every effort to expand the knowledge horizon is useful. Otherwise critical information may not reach nodes far from the source causing dangerous misbehaviour of the swarm. We consider two extreme situations. In the first scenario we have an unique probabilistic delay distribution. In the second scenario, each agent i…
This work provides an extension of Ardupilot's capabilities to allow researchers to develop swarm robotics applications in Robot Operating System(ROS)/Gazebo simulations. Ardupilot is a tool used for autopilot functions in autonomous air, land and underwater robots. However, the original Ardupilot was not designed for applications in the field of swarm robotics. Hence, the main contribution of this paper is to endow Ardupilot with the capability to handle swarm robotics simulations, including the refactoring of the manufacturer's description files. This work offers a comprehensive and realisti…
An intelligent control strategy is proposed to eliminate the actuator saturation problem that exists in the trajectory tracking process of unmanned underwater vehicles (UUV). The control strategy consists of two parts: for the kinematic modeling part, a fuzzy logic-refined backstepping control is developed to achieve control velocities within acceptable ranges and errors of small fluctuations; on the basis of the velocities deducted by the improved kinematic control, the sliding mode control (SMC) is introduced in the dynamic modeling to obtain corresponding torques and forces that should be a…
The University of Manchester（曼彻斯特大学）；Czech Technical University in Prague（布拉格捷克理工大学）；Durham University（杜伦大学）
The recent advancement of Deep Reinforcement Learning (DRL) contributed to robotics by allowing automatic controller design. The automatic controller design is a crucial approach for designing swarm robotic systems, which require more complex controllers than a single robot system to lead a desired collective behaviour. Although the DRL-based controller design method showed its effectiveness, the reliance on the central training server is a critical problem in real-world environments where robot-server communication is unstable or limited. We propose a novel Federated Learning (FL) based DRL t…
Raspi$^2$USBL: An open-source Raspberry Pi-Based Passive Inverted Ultra-Short Baseline Positioning System for Underwater Robotics
State Key Laboratory of Ocean Sensing, Ocean College of Zhejiang University（浙江省海洋传感重点实验室，浙江大学海洋学院）；School of Oceanography, Shanghai Jiao Tong University（上海交通大学海洋学院）
Italian National Agency for New Technologies, Energy and Sustainable Economic Development（意大利新技术、能源与可持续经济发展局）
The subject is the localization problem of an underwater swarm of autonomous underwater robots (AUV), in the frame of the HARNESS project; by localization, we mean the relative swarm configuration, i.e., the geometrical shape of the group. The result is achieved by using the signals that the robots exchange. The swarm is organized by rules and conceived to perform tasks, ranging from environmental monitoring to terrorism-attack surveillance. Two methods of determining the shape of the swarm, both based on trilateration calculation, are proposed. The first method focuses on the robot's speed. I…
On-board Sonar Data Classification for Path Following in Underwater Vehicles using Fast Interval Type-2 Fuzzy Extreme Learning Machine
Hamlyn Centre for Robotic Surgery, Imperial College London（机器人手术哈明中心，帝国理工学院伦敦分校）；Center for Engineering and Industrial Development (CIDESI)（工程与工业发展中心（CIDESI））
This paper presents ongoing research in the SWARMs project towards facilitating context awareness in underwater robots. In particular, the focus of this paper is put on the context reasoning part. The underwater environment introduces uncertainties in context data which lead to difficulties in the context reasoning phase. As probability is the best well-known formalism for computational scientific reasoning under uncertainties, the emerging and effective probabilistic reasoning method, namely, Multi-Entity Bayesian Network (MEBN), is explored for its feasibility to reason under uncertainties i…
FastSLAM is a framework for simultaneous localization using a Rao-Blackwellized particle filter. In FastSLAM, particle filter is used for the mobile robot pose (position and orientation) estimation, and an Extended Kalman Filter (EKF) is used for the feature location's estimation. However, FastSLAM degenerates over time. This degeneracy is due to the fact that a particle set estimating the pose of the robot loses its diversity. One of the main reasons for loosing particle diversity in FastSLAM is sample impoverishment. It occurs when likelihood lies in the tail of the proposal distribution. In…
This paper presents a novel Rapidly-exploring Adaptive Sampling Tree (RAST) algorithm for the adaptive sampling mission of a hybrid aerial underwater vehicle (HAUV) in an air-sea 3D environment. This algorithm innovatively combines the tournament-based point selection sampling strategy, the information heuristic search process and the framework of Rapidly-exploring Random Tree (RRT) algorithm. Hence can guide the vehicle to the region of interest to scientists for sampling and generate a collision-free path for maximizing information collection by the HAUV under the constraints of environmenta…
Carnegie Mellon University（卡内基梅隆大学）；Zhejiang University（浙江大学）；Westlake University（西湖大学）；University of Maryland（马里兰大学）；Westlake Institute for Advanced Study（西湖高等研究院）
Task-Semantic Graph-Driven Distributed Agent Networking for Underwater Target Tracking
College of Computer Science and Software Engineering, Hohai University（河海大学计算机科学与软件工程学院）；College of Information Science and Engineering, Hohai University（河海大学信息科学与工程学院）；Software College, Northeastern University（东北大学软件学院）
