In this paper, we present a control strategy for trajectory tracking and path following of generic paths for underactuated marine vehicles. Our work is inspired and motivated by previous works on ground vehicles. In particular, we extend the definition of the hand position point, introduced for ground vehicles, to autonomous surface vehicles and autonomous underwater vehicles, and then use the hand position point as output for a control strategy based on the input-output feedback linearization method. The presented strategy is able to deal with external disturbances affecting the vehicle, e.g., constant and irrotational ocean currents. Using the Lyapunov analysis, we are able to prove that the closed-loop system has an external dynamics that is globally exponentially stable and an internal dynamics that has ultimately bounded states, both for the trajectory tracking and the path following control problems. Finally, we present a simulation case study and experimental results in order to validate the theoretical results.

This paper describes the open-source software toolchain developed by the Underwater Systems and Technology Laboratory (LSTS) for supporting networked heterogeneous air and ocean vehicle systems. The toolchain supports the deployment of air and ocean vehicles interacting over limited acoustic and wireless networks combined with disruption-tolerant networking protocols. We present the different components of the toolchain and how they can be deployed and extended for different scenarios. We conclude with descriptions of recent applications to onboard deliberative planning and integration of low-cost micro UAVs into the toolchain.

With the growing interest in underwater exploration and monitoring, autonomous underwater vehicles have become essential. The recent interest in onboard deep learning (DL) has advanced real-time environmental interaction capabilities relying on efficient and accurate vision-based DL models. However, the predominant use of sonar in underwater environments, characterized by limited training data and inherent noise, poses challenges to model robustness. This autonomy improvement raises safety concerns for deploying such models during underwater operations, potentially leading to hazardous situations. This article aims to provide the first comprehensive overview of sonar-based DL under the scope of robustness. It studies sonar-based DL perception task models, such as classification, object detection, segmentation, and simultaneous localization and mapping. Furthermore, this article systematizes sonar-based state-of-the-art data sets, simulators, and robustness methods, such as neural network verification, out-of-distribution, and adversarial attacks. This article highlights the lack of robustness in sonar-based DL research and suggests future research pathways, notably establishing a baseline sonar-based data set and bridging the simulation-to-reality gap.

This paper presents the Inter-Module Communication (IMC) protocol, a message-oriented protocol designed and implemented in the Underwater Systems and Technology Laboratory (LSTS) to build interconnected systems of vehicles, sensors and human operators that are able to pursue common goals cooperatively by exchanging real-time information about the environment and updated objectives. IMC abstracts hardware and communication heterogeniety by providing a shared set of messages that can be serialized and transferred over different means. The described protocol contrasts with other existing application level protocols by not imposing or assuming a specific software architecture for client applications. Native support can be automatically generated for different programming languages and/or computer architectures resulting in optimized code which can be used both for networked nodes and also for inter-process and inter-thread communication. The protocol has already been tested throughout various experiments led by LSTS where it has taken care of communications between vehicles, sensors and operator consoles. We are now developing the protocol in the direction of having multi-vehicle cooperation using live data from environmental sensors and mixed-initiative user interaction.

The design and development of the swordfish autonomous surface vehicle (ASV) system is discussed. Swordfish is an ocean capable 4.5 m long catamaran designed for network centric operations (with ocean and air going vehicles and human operators). In the basic configuration, Swordfish is both a survey vehicle and a communications node with gateways for broadband, Wi-Fi and GSM transports and underwater acoustic modems. In another configuration, Swordfish mounts a docking station for the autonomous underwater vehicle Isurus from Porto University. Swordfish has an advanced control architecture for multi-vehicle operations with mixed initiative interactions (human operators are allowed to interact with the control loops).