The automation of typically intelligent and decision-making processes in the maritime industry leads to fewer accidents and more cost-effective operations. However, there are still lots of challenges to solve until fully autonomous systems can be employed. Artificial Intelligence (AI) has played a major role in this paradigm shift and shows great potential for solving some of these challenges, such as the docking process of an autonomous vessel. This work proposes a lightweight volumetric Convolutional Neural Network (vCNN) capable of recognizing different docking-based structures using 3D data in real-time. A synthetic-to-real domain adaptation approach is also proposed to accelerate the training process of the vCNN. This approach makes it possible to greatly decrease the cost of data acquisition and the need for advanced computational resources. Extensive experiments demonstrate an accuracy of over 90% in the recognition of different docking structures, using low resolution sensors. The inference time of the system was about 120ms on average. Results obtained using a real Autonomous Surface Vehicle (ASV) demonstrated that the vCNN trained with the synthetic-to-real domain adaptation approach is suitable for maritime mobile robots. This novel AI recognition method, combined with the utilization of 3D data, contributes to an increased robustness of the docking process regarding environmental constraints, such as rain and fog, as well as insufficient lighting in nighttime operations.INDEX TERMS Autonomous surface vehicle, docking, object recognition, point cloud.

The expansion of autonomous driving operations requires the research and development of accurate and reliable self-localization approaches. These include visual odometry methods, in which accuracy is potentially superior to GNSS-based traditional techniques while also working in signal-denied areas. This paper presents an in-depth review of state-of-the-art methods in visual and point cloud odometry, along with a direct performance comparison of some of these techniques in the autonomous driving context. The evaluated methods include camera, LiDAR, and multi-modal approaches, featuring knowledge and learning-based algorithms. This set was subject to a series of tests on road driving public datasets, from which the performance of these techniques is benchmarked and quantitatively compared. Furthermore, we closely discuss their effectiveness against challenging conditions such as pronounced lighting variations, open spaces, and the presence of dynamic objects in the scene, grouped by categories. The research addresses and corroborates some of the most prominent limitations of state-of-the-art techniques for visual odometry based on 2D and 3D sensors and points out the stagnation, in terms of performance, of the most recent advances in this area, especially in complex environments. We also examine how multi-modal architectures can circumvent these weaknesses and how the current advances in AI constitute a way to overcome the current stagnation, indexing some opportunities for future research.

No abstract