Side-scan sonar imaging data of underwater vehicles for mine detection

Unmanned vehicles have become increasingly popular in the underwater domain in the last decade, as they provide better operation reliability by minimizing human involvement in most tasks. Perception of the environment is crucial for safety and other tasks, such as guidance and trajectory control, mainly when operating underwater. Mine detection is one of the riskiest operations since it involves systems that can easily damage vehicles and endanger human lives if manned. Automating mine detection from side-scan sonar images enhances safety while reducing false negatives. The collected dataset contains 1170 real sonar images taken between 2010 and 2021 using a Teledyne Marine Gavia Autonomous Underwater Vehicle (AUV), which includes enough information to classify its content objects as NOn-Mine-like BOttom Objects (NOMBO) and MIne-Like COntacts (MILCO). The dataset is annotated and can be quickly deployed for object detection, classification, or image segmentation tasks. Collecting a dataset of this type requires a significant amount of time and cost, which increases its rarity and relevance to research and industrial development.

3D hybrid formation control of an underwater robot swarm: Switching topologies, unmeasurable velocities, and system constraints

This paper addresses formation control of underactuated autonomous underwater vehicles in three-dimensional space, using a hybrid protocol that combines aspects of centralized and decentralized control with constraints that are particular to underwater vehicles, including switching topologies, unmeasurable velocities, and system constraints. Using a distributed leader-follower model, the hybrid formation protocol does not require velocity sensing, access to global information, or static and connected topologies. To handle switching jointly connected networks-that is, to tolerate temporary disconnections-a distributed observer is designed for followers to cooperatively estimate leader states using local measurements and local interactions. On this basis, a compound formation control strategy is proposed to achieve geometric convergence. Firstly, cascaded extended state observers are developed to recover the unmeasurable velocities and unknown dynamic uncertainties induced by internal model uncertainty and external disturbances. Secondly, an improved three-dimensional line-of-sight guidance law at the kinematic level is used to address the underactuated configuration and the nonzero attack and sideslip angles. Thirdly, to overcome potential instability as a result of system constraints, including velocity constraints and input saturations, two adaptive compensators in the dynamic controller are used to address the negative effects of truncation. Using the proposed approach, the estimation errors and formation tracking errors are proved to be uniformly and ultimately bounded. Additionally, the numerical simulation results verify the performance of the approach and demonstrate improvement over both distributed and centralized state-of-the-art approaches.

Adaptive model-parameter-free fault-tolerant trajectory tracking control for autonomous underwater vehicles

This paper provides a model-parameter-free control strategy for the trajectory tracking problem of the autonomous underwater vehicle exposed to external disturbances and actuator failures. Two control architectures have been constructed such that the system states could be forced to the desired trajectories with acceptable performance. By combining sliding mode control (SMC) technology and adaptive algorithm, the first control architecture is developed for tracking missions under healthy actuators. Taking actuator failures scenario into account, system reliability is improved considerably by the utilization of a passive fault-tolerant technology in the second controller. Benefitting from properties of Euler-Lagrange systems, the nonlinear dynamics of the underwater vehicles could be handled properly such that the proposed controllers could be developed without model parameters. Finally, the validity of the proposed controllers is demonstrated by theoretical analysis and numerical simulations.

Exo-Ocean Exploration with Deep-Sea Sensor and Platform Technologies

One of Saturn's largest moons, Enceladus, possesses a vast extraterrestrial ocean (i.e., exo-ocean) that is increasingly becoming the hotspot of future research initiatives dedicated to the exploration of putative life. Here, a new bio-exploration concept design for Enceladus' exo-ocean is proposed, focusing on the potential presence of organisms across a wide range of sizes (i.e., from uni- to multicellular and animal-like), according to state-of-the-art sensor and robotic platform technologies used in terrestrial deep-sea research. In particular, we focus on combined direct and indirect life-detection capabilities, based on optoacoustic imaging and passive acoustics, as well as molecular approaches. Such biologically oriented sampling can be accompanied by concomitant geochemical and oceanographic measurements to provide data relevant to exo-ocean exploration and understanding. Finally, we describe how this multidisciplinary monitoring approach is currently enabled in terrestrial oceans through cabled (fixed) observatories and their related mobile multiparametric platforms (i.e., Autonomous Underwater and Remotely Operated Vehicles, as well as crawlers, rovers, and biomimetic robots) and how their modified design can be used for exo-ocean exploration.

An AUV localization and path planning algorithm for terrain-aided navigation

Terrain-aided navigation (TAN) holds high potential for long-term accurate navigation of autonomous underwater vehicles (AUVs), and path planning algorithms are essential in TAN to decrease positioning errors by avoiding flat areas. This study proposed an AUV localization and path planning algorithm for TAN, which consists of a value function calculation and online path planning. In the value function calculation, the topographic complexity is treated as a factor that influences AUV state transition probabilities to calculate the optimal policy; meanwhile, the online path planning applies a particle filter to localize and command AUVs, and particle weights are calculated according to topographic complexity. Simulation experimental results demonstrate that this algorithm could provide paths with accurate TAN location results and good maneuvering performance.

Containment control of networked autonomous underwater vehicles: A predictor-based neural DSC design

This paper investigates the containment control problem of networked autonomous underwater vehicles in the presence of model uncertainty and unknown ocean disturbances. A predictor-based neural dynamic surface control design method is presented to develop the distributed adaptive containment controllers, under which the trajectories of follower vehicles nearly converge to the dynamic convex hull spanned by multiple reference trajectories over a directed network. Prediction errors, rather than tracking errors, are used to update the neural adaptation laws, which are independent of the tracking error dynamics, resulting in two time-scales to govern the entire system. The stability property of the closed-loop network is established via Lyapunov analysis, and transient property is quantified in terms of L2 norms of the derivatives of neural weights, which are shown to be smaller than the classical neural dynamic surface control approach. Comparative studies are given to show the substantial improvements of the proposed new method.