Abstract
This paper address the use of deep learning approaches for visual based navigation in confined underwater environments. State-of-the-art algorithms have shown the tremendous potential deep learning architectures can have for visual navigation implementations, though they are still mostly outperformed by classical feature-based techniques. In this work, we apply current state-of-the-art deep learning methods for visual-based robot navigation to the more challenging underwater environment, providing both an underwater visual dataset acquired in real operational mission scenarios and an assessment of state-of-the-art algorithms on the underwater context. We extend current work by proposing a novel pose optimization architecture for the purpose of correcting visual odometry estimate drift using a Visual-Inertial fusion network, consisted of a neural network architecture anchored on an Inertial supervision learning scheme. Our Visual-Inertial Fusion Network was shown to improve results an average of 50% for trajectory estimates, also producing more visually consistent trajectory estimates for both our underwater application scenarios.

Abstract
Autonomous underwater vehicles are applied in diverse fields, namely in tasks that are risky for human beings to perform, as optical inspection for the purpose of structures quality control. Optical sensors are more appealing cost and they supply a larger quantity of data. Lasers can be used to reconstruct structures in three dimensions, along with cameras, which create a faithful representation of the environment. However, in this context a visual approach was used and the paper presents a method that can put together the three-dimensional information that has been harvested over time, combining also RGB information for surface reconstruction. The map construction follows the motion estimated by a odometry method previously selected from the literature. Experiments conducted using real scenario show that the proposed solution is able to provide a reliable map for objects and even the seafloor.

Abstract
The use of underwater autonomous vehicles has been growing, allowing the performance of tasks that cause inherent risks to Human, namely in inspection processes near to structures. With growth in usage of systems with autonomous navigation, visual acquisition methods have also gotten more developed because, they have appealing cost and they also show interesting results when operate at a short distance. It is possible to improve the quality of navigation through visual SLAM techniques which can map and locate simultaneously and its key aspect is the detection of revisited areas. These techniques are not usually applied to underwater scenarios and, therefore, its performance in environment is unknown. The paper presents a more reliable navigation system for underwater vehicles, resorting to some visual SLAM techniques from literature. The results, conducted in a realistic scenario, demonstrated the ability of the system to be applied to underwater environment.

Abstract
Nowadays, ocean exploration is far from complete and the development of suitable recognition systems are crucial, to allow that the robots perform inspection and monitoring tasks in diverse conditions. The online available datasets are incomplete for these kinds of scenarios and, so it is important to build datasets that covered real condition in a simulated environment. Thus, it was developed a dataset with some man-made objects presents in the underwater environment. Moreover, it is also presented the developed method (Convolutional Neural Network) and its evaluation in diverse conditions is performed. It is also presented a comparative analysis and a discussion between the proposed algorithm and the ResNet architecture. The obtained results showed that the developed method is appropriate to classify 7 critical different objects with good performance.

Abstract
This paper presents a new algorithm for a real-time obstacle avoidance for autonomous surface vehicles (ASV) that is capable of undertaking preemptive actions in complex and challenging scenarios. The algorithm is called adaptive velocity obstacle avoidance (AVOA) and takes into consideration the kinematic and dynamic constraints of autonomous vessels along with a protective zone concept to determine the safe crossing distance to obstacles. A configuration space that includes both the position and velocity of static or dynamic elements within the field-of-view of the ASV is supporting a particle swarm optimization procedure that minimizes the risk of harm and the deviation towards a predefined course while generating a navigation path with capabilities to prevent potential collisions. Extensive experiments demonstrate the ability of AVOA to select a velocity estimative for ASVs that originates a smoother, safer and, at least, two times more effective collision-free path when compared to existing techniques.

Abstract
This paper presents the results from search and rescue missions performed with the aerial robot OTUS in the the context of the ISEP/INESC TEC aerial robotics team participation on the euRathlon 2015 robotics competition. The multi-domain (land, sea and air) search and rescue scenario is described and technical solution adopted is presented with emphasis on the perception system. The calibration of the image based system is addressed. Results from the operational missions performed are also discussed. The aerial autonomous vehicle was able to successfully perform multiple tasks from the aerial reconnaissance and 3D mapping to the identification of leaking pipes, obstructed passages and missing workers. The system was validated a realistic operational scenario and won the Grand Challenge in cooperation with land and marine robotics partner teams. This challenge was the first time that a real time collaborative team of aerial, land and marine robots was deployed successfully in a search and rescue mission.