Abstract
Over the last few years, oil spill incidents occured with some regularity during exploration, production and transportation, causing a large economic and ecologic impact in the world community. To minimise these impacts and reduce the time response of the initial mitigation process, autonomous vehicles, such as unmanned aerial vehicles (UAV) can be used to perform oil spill monitoring and mitigation. This paper presents the design and implementation of a multirotor UAV capable of identifying and combat the oil spill, by using a release system of consortia with bacteria and nutrients. Several field tests occurred in Portugal and Spain, where the oil spill was implemented in a simulated environment, resulting in a cooperative and simultaneous manoeuvre between the vehicles.

Abstract
The overall aim of the ROSM project is the implementation of an innovative solution based on heterogeneous autonomous vehicles to tackle maritime pollution (in particular, oil spills). These solutions will be based on native microbial consortia with bioremediation capacity, and the adaptation of air and surface autonomous vehicles for in-situ release of autochthonous microorganisms (bioaugmentation) and nutrients (biostimulation). By doing so, these systems can be used as the first line of the responder to pollution incidents from several origins that may occur inside ports, around industrial and extraction facilities, or during transport activities, in a fast, efficient and low-cost way. The paper will address the development of a team of autonomous vehicles able to carry, as payload, native organisms to naturally degrade oil spills (avoiding the introduction of additional chemical or biological additives), the development of a multi-robot system able to provide a first line responses to oil spill incidents under unfavourable and harsh conditions with low human intervention, and then a decentralized cooperative planning with the ability to coordinate an efficient oil spill combat. Field tests have been performed in Leixoes Harbour in Porto and Medas, Portugal, with a simulated oil spill and validated the decentralized coordinated task between the autonomous surface vehicle (ASV) ROAZ and the unmanned aerial vehicle (UAV).

Abstract
This paper presents an innovative modular autonomous underwater vehicle (MARA) developed for the exploration of underwater confined spaces such as underwater caves, flooded underground mines or complex tight infrastructures in underwater environments. The particular mission scenario of exploration of flooded underground mines was used as a key driver for the robot development. The autonomous underwater vehicle is described from the mechanical, hardware and software points of view. The availability of the INESC TEC underwater systems test tank and access conditions to Porto harbour and the Urgeirica mine allows for easy robot field validation. Preliminary results are also presented and discussed.

Abstract
This paper presents an autonomous robotic system, IRIS, designed for lost fishing gear recovery. The vehicle was developed in the context of the NetTag project. This is a European Union project funded by EASME the Executive Agency for Small and Medium Enterprises addressing marine litter, and the reduction of quantity and impact of lost fishing gears in the ocean. NetTag intends to produce new technological devices for location and recovery of fishing gear and educational material about marine litter, raise awareness of fisheries industry and other stakeholders about the urgent need to combat marine litter and increase scientific knowledge on marine litter problematic, guaranteeing the engagement of fishers to adopt better practices to reduce and prevent marine litter derived from fisheries. The design of IRIS is presented in detail, addressing the mechanical design, hardware architecture, sensor system and navigation and control. Preliminary tests in tank and in controlled sea conditions are presented and ongoing developments on the recovery system are discussed.

Abstract
This paper addresses the development of a remote hyperspectral imaging system for detection and characterization of marine litter concentrations in an oceanic environment. The work performed in this paper is the following: (i) an in-situ characterization was conducted in an outdoor laboratory environment with the hyperspectral imaging system to obtain the spatial and spectral response of a batch of marine litter samples; (ii) a real dataset hyperspectral image acquisition was performed using manned and unmanned aerial platforms, of artificial targets composed of the material analyzed in the laboratory; (iii) comparison of the results (spatial and spectral response) obtained in laboratory conditions with the remote observation data acquired during the dataset flights; (iv) implementation of two different supervised machine learning methods, namely Random Forest (RF) and Support Vector Machines (SVM), for marine litter artificial target detection based on previous training. Obtained results show a marine litter automated detection capability with a 70-80% precision rate of detection in all three targets, compared to ground-truth pixels, as well as recall rates over 50%.

Abstract
This work addresses the use of hyperspectral imaging systems for remote detection of marine litter concentrations in oceanic environments. The work consisted on mounting an off-the-shelf hyperspectral imaging system (400-2500 nm) in two aerial platforms: manned and unmanned, and performing data acquisition to develop AI methods capable of detecting marine litter concentrations at the water surface. We performed the campaigns at Porto Pim Bay, Fail Island, Azores, resorting to artificial targets built using marine litter samples. During this work, we also developed a Convolutional Neural Network (CNN-3D), using spatial and spectral information to evaluate deep learning methods to detect marine litter in an automated manner. Results show over 84% overall accuracy (OA) in the detection and classification of the different types of marine litter samples present in the artificial targets.