Abstract
Soil Moisture (SM) is one of the most critical factors for a crop's growth, yield, and quality. Although Ground-Penetrating RADAR (GPR) is commonly used in satelite observation to analyze soil moisture, it is not cost-effective for agricultural applications. Automotive RADAR uses the concept of Frequency-Modulated Continuous Wave (FMCW) and is more competitive in terms of price. This paper evaluates the viability of using a cost-effective RADAR as a substitute for GPR for soil moisture content estimation. The research consisted of four experiments, and the results show that the RADAR's output signal and the soil moisture sensor SEN0193 have a high correlation with values as high as 0.93 when the SM is below 15%. Such results show that the tested sensor (and its cost-effective working principle) are able to determine soil water content (with certain limitations) in a non-intrusive, proximal sensing manner.

Abstract
Object identification, such as tree trunk detection, is fundamental for forest robotics. Intelligent vision systems are of paramount importance in order to improve robotic perception, thus enhancing the autonomy of forest robots. To that purpose, this paper presents three contributions: an open dataset of 5325 annotated forest images; a tree trunk detection Edge AI benchmark between 13 deep learning models evaluated on four edge-devices (CPU, TPU, GPU and VPU); and a tree trunk mapping experiment using an OAK-D as a sensing device. The results showed that YOLOR was the most reliable trunk detector, achieving a maximum F1 score around 90% while maintaining high scores for different confidence levels; in terms of inference time, YOLOv4 Tiny was the fastest model, attaining 1.93 ms on the GPU. YOLOv7 Tiny presented the best trade-off between detection accuracy and speed, with average inference times under 4 ms on the GPU considering different input resolutions and at the same time achieving an F1 score similar to YOLOR. This work will enable the development of advanced artificial vision systems for robotics in forestry monitoring operations.

Abstract

Abstract

Abstract
The Open Laboratory of Interdisciplinary Experimentation (LAEI) had its 1st edition as UC "lnovPed" in the academic year 2018/2019, resulting from a proposal presented by professors from the Faculty of Arts, Faculty of Engineering and collaborators of the U. Porto. Imp1ementing the U.OpenLah concept and involving students from different degrees and scientific areas, LAEI has sought to develop basic skills and added value in creating digital experiences. Through theoretical exposition and an experimentation exercise in the field of digital content production or technologies for innovative digital content, creativity and project management, students share and implement the concepts and competences learned, including those of the scientific area of origin.

Abstract
In order to study the behavior and performance of a robot, building its simulation model is crucial. Realistic simulation tools using physics engines enable faster, more accurate and realistic testing conditions, without depending on the real vehicle. By combining legged and wheeled locomotion, hybrid vehicles are specially useful for operating in different types of terrains, both indoors and outdoors. They present increased mobility, versatility and adaptability, as well as easier maneuverability, when compared to vehicles using only one of the mechanisms. This paper presents the realistic simulation through the SimTwo simulator software of a hybrid legged-wheeled robot. It has four 3-DOF (degrees of freedom) legs combining rigid and non-rigid joints and has been fully designed, tested and validated in the simulated environment with incorporated dynamics.