Sustainable Solutions for Sea Monitoring With Robotic Sailboats: N-Boat and F-Boat Twins.

Strategic management and production of internal energy in autonomous robots is becoming a research topic with growing importance, especially for platforms that target long-endurance missions, with long-range and duration. It is fundamental for autonomous vehicles to have energy self-generation capability to improve energy autonomy, especially in situations where refueling is not viable, such as an autonomous sailboat in ocean traversing. Hence, the development of energy estimation and management solutions is an important research topic to better optimize the use of available energy supply and generation potential. In this work, we revisit the challenges behind the project design and construction for two fully autonomous sailboats and propose a methodology based on the Restricted Boltzmann Machine (RBM) in order to find the best way to manage the supplementary energy generated by solar panels. To verify the approach, we introduce a case study with our two developed sailboats that have planned payload with electric and electronics, and one of them is equipped with an electrical engine that may eventually help with the sailboat propulsion. Our current results show that it is possible to augment the system confidence level for the potential energy that can be harvested from the environment and the remaining energy stored, optimizing the energy usage of autonomous vehicles and improving their energy robustness.

Multivariate data driven prediction of COVID-19 dynamics: Towards new results with temperature, humidity and air quality data.

Since the start of the COVID-19 pandemic many studies investigated the correlation between climate variables such as air quality, humidity and temperature and the lethality of COVID-19 around the world. In this work we investigate the use of climate variables, as additional features to train a data-driven multivariate forecast model to predict the short-term expected number of COVID-19 deaths in Brazilian states and major cities. The main idea is that by adding these climate features as inputs to the training of data-driven models, the predictive performance improves when compared to equivalent single input models. We use a Stacked LSTM as the network architecture for both the multivariate and univariate model. We compare both approaches by training forecast models for the COVID-19 deaths time series of the city of São Paulo. In addition, we present a previous analysis based on grouping K-means on AQI curves. The results produced will allow achieving the application of transfer learning, once a locality is eventually added to the task, regressing out using a model based on the cluster of similarities in the AQI curve. The experiments show that the best multivariate model is more skilled than the best standard data-driven univariate model that we could find, using as evaluation metrics the average fitting error, average forecast error, and the profile of the accumulated deaths for the forecast. These results show that by adding more useful features as input to a multivariate approach could further improve the quality of the prediction models.

A Methodological Approach to the Learning of Robotics with EDUROSC-Kids.

With advances in science and technology, several innovative researches have been developed trying to figure out the main problems related to children's learning. It is known that issues such as frustration and inattention, between others, affect student learning. In this fashion, robotics is an important resource that can be used towards helping to solve these issues, empowering our students in order to push their learning up. In this case, robotic tools are generally used considering two different paradigms: as the main focus and as a secondary focus. Actually, these paradigms define the way that Educational Robotics is implemented in schools. Most of the approaches have implemented it as the main focus, which is teaching Robotics. Nevertheless, there are quite a few works that implement robotics as a secondary focus, which is currently assisting the learning process in several disciplines. The main contribution of this work is a complete three steps methodology for Robotics in Education to guide projects in order to either use it alone or to teach robotics with others topics. Our experiments show the importance of devising a study plan and evaluation method because the process is iterative and could improve the final results. As a novelty, here we have joined and extended our previous works by proposing a new set of methods with guidelines and strategies for applying the educational robotics standard curriculum for kids, named EDUROSC-Kids. We propose several tools that have been developed to organize the learning topics of Robotics for children, including the desired outcomes during the learning process. As said our current approach is divided in three steps (or phases): setting up the environment, defining the project, and performing evaluation. The proposed curriculum organizes robotics contents into five disciplines: Robotics and Society, Mechanics, Electronics, Programming, and Control Theory. Also, it considers a set of topics for each discipline and defines the level of knowledge that is recommended to achieve each group of children based on Bloom's Nomenclature. The contribution on this paper is a crucial step towards linking the general learning process with Educational Robotics approaches. Our methodology is validated by presenting practical experiences with application of EDUROSC-kids and the proposed method with a rubric guidelines into groups of children.

Smart Artificial Markers for Accurate Visual Mapping and Localization.

Artificial marker mapping is a useful tool for fast camera localization estimation with a certain degree of accuracy in large indoor and outdoor environments. Nonetheless, the level of accuracy can still be enhanced to allow the creation of applications such as the new Visual Odometry and SLAM datasets, low-cost systems for robot detection and tracking, and pose estimation. In this work, we propose to improve the accuracy of map construction using artificial markers (mapping method) and camera localization within this map (localization method) by introducing a new type of artificial marker that we call the smart marker. A smart marker consists of a square fiducial planar marker and a pose measurement system (PMS) unit. With a set of smart markers distributed throughout the environment, the proposed mapping method estimates the markers' poses from a set of calibrated images and orientation/distance measurements gathered from the PMS unit. After this, the proposed localization method can localize a monocular camera with the correct scale, directly benefiting from the improved accuracy of the mapping method. We conducted several experiments to evaluate the accuracy of the proposed methods. The results show that our approach decreases the Relative Positioning Error (RPE) by 85% in the mapping stage and Absolute Trajectory Error (ATE) by 50% for the camera localization stage in comparison with the state-of-the-art methods present in the literature.

A Survey on Unmanned Surface Vehicles for Disaster Robotics: Main Challenges and Directions.

Disaster robotics has become a research area in its own right, with several reported cases of successful robot deployment in actual disaster scenarios. Most of these disaster deployments use aerial, ground, or underwater robotic platforms. However, the research involving autonomous boats or Unmanned Surface Vehicles (USVs) for Disaster Management (DM) is currently spread across several publications, with varying degrees of depth, and focusing on more than one unmanned vehicle-usually under the umbrella of Unmanned Marine Vessels (UMV). Therefore, the current importance of USVs for the DM process in its different phases is not clear. This paper presents the first comprehensive survey about the applications and roles of USVs for DM, as far as we know. This work demonstrates that there are few current deployments in disaster scenarios, with most of the research in the area focusing on the technological aspects of USV hardware and software, such as Guidance Navigation and Control, and not focusing on their actual importance for DM. Finally, to guide future research, this paper also summarizes our own contributions, the lessons learned, guidelines, and research gaps.

A Versatile Method for Depth Data Error Estimation in RGB-D Sensors.

We propose a versatile method for estimating the RMS error of depth data provided by generic 3D sensors with the capability of generating RGB and depth (D) data of the scene, i.e., the ones based on techniques such as structured light, time of flight and stereo. A common checkerboard is used, the corners are detected and two point clouds are created, one with the real coordinates of the pattern corners and one with the corner coordinates given by the device. After a registration of these two clouds, the RMS error is computed. Then, using curve fittings methods, an equation is obtained that generalizes the RMS error as a function of the distance between the sensor and the checkerboard pattern. The depth errors estimated by our method are compared to those estimated by state-of-the-art approaches, validating its accuracy and utility. This method can be used to rapidly estimate the quality of RGB-D sensors, facilitating robotics applications as SLAM and object recognition.

Efficient 3D Objects Recognition Using Multifoveated Point Clouds.

Technological innovations in the hardware of RGB-D sensors have allowed the acquisition of 3D point clouds in real time. Consequently, various applications have arisen related to the 3D world, which are receiving increasing attention from researchers. Nevertheless, one of the main problems that remains is the demand for computationally intensive processing that required optimized approaches to deal with 3D vision modeling, especially when it is necessary to perform tasks in real time. A previously proposed multi-resolution 3D model known as foveated point clouds can be a possible solution to this problem. Nevertheless, this is a model limited to a single foveated structure with context dependent mobility. In this work, we propose a new solution for data reduction and feature detection using multifoveation in the point cloud. Nonetheless, the application of several foveated structures results in a considerable increase of processing since there are intersections between regions of distinct structures, which are processed multiple times. Towards solving this problem, the current proposal brings an approach that avoids the processing of redundant regions, which results in even more reduced processing time. Such approach can be used to identify objects in 3D point clouds, one of the key tasks for real-time applications as robotics vision, with efficient synchronization allowing the validation of the model and verification of its applicability in the context of computer vision. Experimental results demonstrate a performance gain of at least 27.21% in processing time while retaining the main features of the original, and maintaining the recognition quality rate in comparison with state-of-the-art 3D object recognition methods.

A wearable mobile sensor platform to assist fruit grading.

Wearable computing is a form of ubiquitous computing that offers flexible and useful tools for users. Specifically, glove-based systems have been used in the last 30 years in a variety of applications, but mostly focusing on sensing people's attributes, such as finger bending and heart rate. In contrast, we propose in this work a novel flexible and reconfigurable instrumentation platform in the form of a glove, which can be used to analyze and measure attributes of fruits by just pointing or touching them with the proposed glove. An architecture for such a platform is designed and its application for intuitive fruit grading is also presented, including experimental results for several fruits.

Method for reading sensors and controlling actuators using audio interfaces of mobile devices.

This article presents a novel closed loop control architecture based on audio channels of several types of computing devices, such as mobile phones and tablet computers, but not restricted to them. The communication is based on an audio interface that relies on the exchange of audio tones, allowing sensors to be read and actuators to be controlled. As an application example, the presented technique is used to build a low cost mobile robot, but the system can also be used in a variety of mechatronics applications and sensor networks, where smartphones are the basic building blocks.