Abstract
In this paper a vision based groundtruth system for underwater applications is presented. The proposed system as an external validation perception and localization mechanism for underwater trials in the INESC TEC/ISEP underwater robotics test tank. It is comprised by a stereo camera pair with external synchronization and a image processing and data recording host computer. The cameras are disposed in a rigid baseline calibrated using scenario key points. Two target detection algorithms were tested and their results are discussed. One is based on template matching techniques allowing the tracking of arbitrary targets without particular markers and the other on color segmentation with the target vehicle equipped with light markers. Also an example trajectory of a small ROV motion in the task is also presented.

Abstract
In this paper, we propose a cooperative perception framework for multi-robot real-time 3D high dynamic target estimation in outdoor scenarios based on monocular camera available on each robot. The relative position and orientation between robots establishes a flexible and dynamic stereo baseline. Overlap views subject to geometric constraints emerged from the stereo formulation, which allowed us to obtain a decentralized cooperative perception layer. Epipolar constraints related to the global frame are applied both in image feature matching and to feature searching and detection optimization in the image processing of robots with low computational capabilities. In contrast to classic stereo, the proposed framework considers all sources of uncertainty (in localization, attitude and image detection from both robots) in the determination of the objects best 3D localization and its uncertainty. The proposed framework can be later integrated in a decentralized data fusion (DDF) multi-target tracking approach where it can contribute to reduce rumor propagation data association and track initialization issues. We demonstrate the advantages of this approach in real outdoor scenario. This is done by comparing a stereo rigid baseline standalone target tracking with the proposed multi-robot cooperative stereo between a micro aerial vehicle (MAV) and an autonomous ground vehicle (AGV).

Abstract
In this paper we present an autonomous ground robot developed for outdoor applications in unstructured scenarios. The robot was developed as a versatile robotics platform for development, test and validation of research in navigation, control, perception and multiple robot coordination on all terrain scenarios. The hybrid systems approach to the control architecture is discussed in the context of multiple robot coordination. The robot modular hardware and software architecture allows for a wide range of mission applications. A precise navigation system based on high accuracy GPS is used for accurate 3D environment mapping tasks. The vision system is also presented along with some example results from stereo target tracking in operational environment.

Abstract
Robotics research in Portugal is increasing every year, but few students embrace it as one of their first choices for study. Until recently, job offers for engineers were plentiful, and those looking for a degree in science and technology would avoid areas considered to be demanding, like robotics. At the undergraduate level, robotics programs are still competing for a place in the classical engineering graduate curricula. Innovative and dynamic Master's programs may offer the solution to this gap. The Master's degree in autonomous systems at the Instituto Superior de Engenharia do Porto (ISEP), Porto, Portugal, was designed to provide a solid training in robotics and has been showing interesting results, mainly due to differences in course structure and the context in which students are welcomed to study and work.

Abstract
We present a novel approach to 6D visual odometry for vehicles with calibrated stereo cameras. A dense probabilistic egomotion (5D) method is combined with robust stereo feature based approaches and Extended Kalman Filtering (EKF) techniques to provide high quality estimates of vehicle's angular and linear velocities. Experimental results show that the proposed method compares favorably with state-the-art approaches, mainly in the estimation of the angular velocities, where significant improvements are achieved.

Abstract
The robotics community is concerned with the ability to infer and compare the results from researchers in areas such as vision perception and multi-robot cooperative behavior. To accomplish that task, this paper proposes a real-time indoor visual ground truth system capable of providing accuracy with at least more magnitude than the precision of the algorithm to be evaluated. A multi-camera architecture is proposed under the ROS (Robot Operating System) framework to estimate the 3D position of objects and the implementation and results were contextualized to the Robocup Middle Size League scenario.