Browsing by Author "Silva, Eduardo"
Now showing 1 - 10 of 47
Results Per Page
Sort Options
- 6D Visual Odometry with Dense Probabilistic Egomotion EstimationPublication . Silva, Hugo Miguel; Bernardino, Alexandre; Silva, EduardoWe 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.
- Application of Visual-Inertial SLAM for 3D Mapping of Underground EnvironmentsPublication . Ferreira, António Bernardo; Almeida, José Miguel; Silva, EduardoThe underground scenarios are one of the most challenging environments for accurate and precise 3d mapping where hostile conditions like absence of Global Positioning Systems, extreme lighting variations and geometrically smooth surfaces may be expected. So far, the state-of-the-art methods in underground modelling remain restricted to environments in which pronounced geometric features are abundant. This limitation is a consequence of the scan matching algorithms used to solve the localization and registration problems. This paper contributes to the expansion of the modelling capabilities to structures characterized by uniform geometry and smooth surfaces, as is the case of road and train tunnels. To achieve that, we combine some state of the art techniques from mobile robotics, and propose a method for 6DOF platform positioning in such scenarios, that is latter used for the environment modelling. A visual monocular Simultaneous Localization and Mapping (MonoSLAM) approach based on the Extended Kalman Filter (EKF), complemented by the introduction of inertial measurements in the prediction step, allows our system to localize himself over long distances, using exclusively sensors carried on board a mobile platform. By feeding the Extended Kalman Filter with inertial data we were able to overcome the major problem related with MonoSLAM implementations, known as scale factor ambiguity. Despite extreme lighting variations, reliable visual features were extracted through the SIFT algorithm, and inserted directly in the EKF mechanism according to the Inverse Depth Parametrization. Through the 1-Point RANSAC (Random Sample Consensus) wrong frame-to-frame feature matches were rejected. The developed method was tested based on a dataset acquired inside a road tunnel and the navigation results compared with a ground truth obtained by post-processing a high grade Inertial Navigation System and L1/L2 RTK-GPS measurements acquired outside the tunnel. Results from the localization strategy are presented and analyzed.
- Autonomous Surface Vehicle Docking Manoeuvre with Visual InformationPublication . Martins, Alfredo; Almeida, José Miguel; Ferreira, Hugo; Silva, Hugo; Dias, Nuno; Silva, EduardoThis work presents a hybrid coordinated manoeuvre for docking an autonomous surface vehicle with an autonomous underwater vehicle. The control manoeuvre uses visual information to estimate the AUV relative position and attitude in relation to the ASV and steers the ASV in order to dock with the AUV. The AUV is assumed to be at surface with only a small fraction of its volume visible. The system implemented in the autonomous surface vehicle ROAZ, developed by LSA-ISEP to perform missions in river environment, test autonomous AUV docking capabilities and multiple AUV/ASV coordinated missions is presented. Information from a low cost embedded robotics vision system (LSAVision), along with inertial navigation sensors is fused in an extended Kalman filter and used to determine AUV relative position and orientation to the surface vehicle The real time vision processing system is described and results are presented in operational scenario.
- Ball Sensing in a Leg Like Robotic KickerPublication . Logghe, Jonas; Dias, André; Almeida, José Miguel; Martins, Alfredo; Silva, EduardoThe trend to have more cooperative play and the increase of game dynamics in Robocup MSL League motivates the improvement of skills for ball passing and reception. Currently the majority of the MSL teams uses ball handling devices with rollers to have more precise kicks but limiting the capability to kick a moving ball without stopping it and grabbing it. This paper addresses the problem to receive and kick a fast moving ball without having to grab it with a roller based ball handling device. Here, the main difficulty is the high latency and low rate of the measurements of the ball sensing systems, based in vision or laser scanner sensors.Our robots use a geared leg coupled to a motor that acts simultaneously as the kicking device and low level ball sensor. This paper proposes a new method to improve the capability for ball sensing in the kicker, by combining high rate measurements from the torque and energy in the motor and angular position of the kicker leg. The developed method endows the kicker device with an effective ball detection ability, validated in several game situations like in an interception to a fast pass or when chasing the ball where the relative speed from robot to ball is low. This can be used to optimize the kick instant or by the embedded kicker control system to absorb the ball energy.
- BoaVista – Sensor Dedicado de Visão Artificial Baseado em Hardware (Re)configurávelPublication . Lima, Luís; Almeida, José; Martins, Alfredo; Silva, EduardoEste artigo aborda o projecto de um sistema de visão dedicado para robótica móvel autónoma, que beneficia das capacidades de execução paralela do hardware reconfigurável, processando em “pipeline” as imagens provenientes de um sensor de imagem CMOS de alto desempenho em simultâneo com a aquisição das mesmas. Apresentamos um sistema com a capacidade de adquirir e processar imagens com resoluções de 640x480 a uma taxa de 60 fps, baixo custo e capaz de disponibilizar para o sistema central apenas a informação pretendida extraída da imagem. Este ponto, permite libertar os recursos computacionais do robot traduzindo-se em reduções de consumo significativas e consequente aumento da autonomia energética do mesmo.
- Calibration Method for Underwater Visual Ground-Truth SystemPublication . Faria, André; Almeida, José; Dias, André; Martins, Alfredo; Silva, EduardoThis work presents an automatic calibration method for a vision based external underwater ground-truth positioning system. These systems are a relevant tool in benchmarking and assessing the quality of research in underwater robotics applications. A stereo vision system can in suitable environments such as test tanks or in clear water conditions provide accurate position with low cost and flexible operation. In this work we present a two step extrinsic camera parameter calibration procedure in order to reduce the setup time and provide accurate results. The proposed method uses a planar homography decomposition in order to determine the relative camera poses and the determination of vanishing points of detected lines in the image to obtain the global pose of the stereo rig in the reference frame. This method was applied to our external vision based ground-truth at the INESC TEC/Robotics test tank. Results are presented in comparison with an precise calibration performed using points obtained from an accurate 3D LIDAR modelling of the environment.
- Combining sparse and dense methods in 6D Visual OdometryPublication . Silva, Hugo Miguel; Silva, Eduardo; Bernardino, AlexandreVisual Odometry is one of the most powerful, yet challenging, means of estimating robot ego-motion. By grounding perception to the static features in the environment, vision is able, in principle, to prevent the estimation bias rather common in other sensory modalities such as inertial measurement units or wheel odometers. We present a novel approach to ego-motion estimation of a mobile robot by using a 6D Visual Odometry Probabilistic Approach. Our approach exploits the complementarity of dense optical flow methods and sparse feature based methods to achieve 6D estimation of vehicle motion. A dense probabilistic method is used to robustly estimate the epipolar geometry between two consecutive stereo pairs; a sparse feature stereo approach to estimate feature depth; and an Absolute Orientation method like the Procrustes to estimate the global scale factor. We tested our proposed method on a known dataset and compared our 6D Visual Odometry Probabilistic Approach without filtering techniques against a implementation that uses the well known 5-point RANSAC algorithm. Moreover, comparison with an Inertial Measurement Unit (RTK-GPS) is also performed, for providing a more detailed evaluation of the method against ground-truth information.
- Control and Localisation for the ISePorto Robotic Soccer TeamPublication . Almeida, José; Martins, Alfredo; Silva, EduardoThis paper describes the control and localisation design and implementation status of the ISePorto robotic football team for participation in Robocup Middle Size League (F2000). The objectives guiding the project were the applications and research in hybrid control and coordination systems. The system has also an educational support role. A special attention is made to the custom design to allow the execution of complex manoeuvres and team coordinated behaviours. The robot has different pass, shot, and manoeuvre capabilities providing high level tactical and strategic planing and coordination.
- Coordinated Maneuver for Gradient Search Using Multiple AUV'sPublication . Martins, Alfredo; Almeida, José; Silva, EduardoThe coordinated use of multiple Autonomous Underwater Vehicles can provide important advantages for oceanographic missions. One important mission application scenario can be the search of underwater plumes such as sources of freshwater of hydrothermal vents. These plumes characterize the environment by creating a gradient field of some measurable physical quantity. An innovative integrated acoustic navigation system and coordination control maneuver for a formation of 3 AUVs and 1 surface craft to gradient search and following missions is proposed. The specific formation geometry and topology takes in account the navigation and coordination requirements. It was designed to achieve an efficient, low cost and technically feasible solution. The system can operate in 3 modes depending on formation distances. Varying pinging rates and offsets are used to communicate parameters and mode changing. No additional underwater communication systems neither acoustic transponder deployment are needed for the vehicle coordination. This way a high degree of energy efficiency and overall mission low cost and simpler logistics is achieved. The hybrid nature of the coordinating maneuver allows the formation gradient survey and following with the efficient exploitation of the environment structuring by the phenomena to be studied. The individual control laws were designed in order to minimize the inter-vehicle communication. The coordination factors are the knowledge by the vehicles of each other behavior (since all vehicles execute the same control laws) and the detection of formation distortions. These distortions are detected by the relative navigation system. The proposed approach allows the low cost implementation of a multiple AUV coordinating control for a large range of oceanographic missions.
- Decentralized Target Tracking based on Multi-Robot Cooperative TriangulationPublication . Dias, André; Capitan, J.; Merino, L.; Almeida, José; Lima, Pedro; Silva, EduardoTarget tracking with bearing-only sensors is a challenging problem when the target moves dynamically in complex scenarios. Besides the partial observability of such sensors, they have limited field of views, occlusions can occur, etc. In those cases, cooperative approaches with multiple tracking robots are interesting, but the different sources of uncertain information need to be considered appropriately in order to achieve better estimates. Even though there exist probabilistic filters that can estimate the position of a target dealing with incertainties, bearing-only measurements bring usually additional problems with initialization and data association. In this paper, we propose a multi-robot triangulation method with a dynamic baseline that can triangulate bearing-only measurements in a probabilistic manner to produce 3D observations. This method is combined with a decentralized stochastic filter and used to tackle those initialization and data association issues. The approach is validated with simulations and field experiments where a team of aerial and ground robots with cameras track a dynamic target.