This paper presents results of the INESC TEC participation in the maritime environment (both at surface and underwater) integrated in the ICARUS team in the euRathlon 2015 robotics search and rescue competition. These relate to the marine robots from INESC TEC, surface (ROAZ USV) and underwater (MARES AUV) autonomous vehicles participation in multiple tasks such as situation assessment, underwater mapping, leak detection or victim localization. This participation was integrated in the ICARUS Team resulting of the EU funded project aimed to develop robotic tools for large scale disasters. The coordinated search and rescue missions were performed with an initial surface survey providing data for AUV mission planning and execution. A situation assessment bathymetry map, sidescan sonar imaging and location of structures, underwater leaks and victims were achieved, with the global ICARUS team (involving sea, air and land coordinated robots) participating in the final grand Challenge and achieving the second place.
This paper presents a high performance (low computationally demanding) monocular vision-based system for a hovering Autonomous Underwater Vehicle (AUV) in the context of autonomous docking process-MViDO system: Monocular Vision-based Docking Operation aid. The MViDO consists of three sub-modules: a pose estimator, a tracker and a guidance sub-module. The system is based on a single camera and a three spherical color markers target that signal the docking station. The MViDO system allows the pose estimation of the three color markers even in situations of temporary occlusions, being also a system that rejects outliers and false detections. This paper also describes the design and implementation of the MViDO guidance module for the docking manoeuvres. We address the problem of driving the AUV to a docking station with the help of the visual markers detected by the on-board camera, and show that by adequately choosing the references for the linear degrees of freedom of the AUV, the AUV is conducted to the dock while keeping those markers in the field of view of the on-board camera. The main concepts behind the MViDO are provided and a complete characterization of the developed system is presented from the formal and experimental point of view. To test and evaluate the MViDO detector and pose an estimator module, we created a ground truth setup. To test and evaluate the tracker module we used the MARES AUV and the designed target in a four-meter tank. The performance of the proposed guidance law was tested on simulink/Matlab.
Currently, Unmanned Aerial Vehicles (UAVs) are considered in the development of various applications in agriculture, which has led to the expansion of the agricultural UAV market. However, Nano Aerial Vehicles (NAVs) are still underutilised in agriculture. NAVs are characterised by a maximum wing length of 15 centimetres and a weight of fewer than 50 g. Due to their physical characteristics, NAVs have the advantage of being able to approach and perform tasks with more precision than conventional UAVs, making them suitable for precision agriculture. This work aims to contribute to an open-source solution known as Nano Aerial Bee (NAB) to enable further research and development on the use of NAVs in an agricultural context. The purpose of NAB is to mimic and assist bees in the context of pollination. We designed this open-source solution by taking into account the existing state-of-the-art solution and the requirements of pollination activities. This paper presents the relevant background and work carried out in this area by analysing papers on the topic of NAVs. The development of this prototype is rather complex given the interactions between the different hardware components and the need to achieve autonomous flight capable of pollination. We adequately describe and discuss these challenges in this work. Besides the open-source NAB solution, we train three different versions of YOLO (YOLOv5, YOLOv7, and YOLOR) on an original dataset (Flower Detection Dataset) containing 206 images of a group of eight flowers and a public dataset (TensorFlow Flower Dataset), which must be annotated (TensorFlow Flower Detection Dataset). The results of the models trained on the Flower Detection Dataset are shown to be satisfactory, with YOLOv7 and YOLOR achieving the best performance, with 98% precision, 99% recall, and 98% F1 score. The performance of these models is evaluated using the TensorFlow Flower Detection Dataset to test their robustness. The three YOLO models are also trained on the TensorFlow Flower Detection Dataset to better understand the results. In this case, YOLOR is shown to obtain the most promising results, with 84% precision, 80% recall, and 82% F1 score. The results obtained using the Flower Detection Dataset are used for NAB guidance for the detection of the relative position in an image, which defines the NAB execute command.
This paper presents the last developments towards vision-based target tracking by an AUV. The main concepts behind the visual relative localization are provided and the results from a statistical analysis for the relative localization algorithm are presented. The purpose of this analysis is to ensure properness of data used to feed controllers that are responsible for governing the AUV motion. A new set of controllers enabling the AUV to track a visual target is given. Experimental data from obtained from tests in tank are presented, validating both the visual relative localization and control of the AUV.
This paper presents the development of a first approach to a vision-based target detection. The ultimate objective of this work is to position an autonomous surface vehicle relative to a target. Experiments in a controlled indoor environment were conducted to test the developed system. The experimental results are analyzed and show that the tracking performances achieve errors in the order of a few centimetres.