TeCIP Institute

L'Aquila, Italy

TeCIP Institute

L'Aquila, Italy
Time filter
Source Type

Di Fava A.,Sant'Anna School of Advanced Studies | Satler M.,TeCIP Institute | Tripicchio P.,TeCIP Institute
2015 23rd Mediterranean Conference on Control and Automation, MED 2015 - Conference Proceedings | Year: 2015

In many applications, robots should be able to move autonomously in semi-structured or unstructured environments. Autonomous robots can be employed for instance in area patrolling tasks in order to perform surveillance of sites. To autonomously navigate in an unknown outdoor scenario, a robot should be able to acquire sensible information about the environment by means of its own sensors and at the same time perform some reasoning to decide where and how to move. In this paper, we present a vision-based solution for the decision making and a behavior based low-level control for the navigation. Three different testing scenarios have been employed to assess the capabilities of the proposed approach: a computer simulated scenario, an indoor test on a real robotic platform and finally an outdoor test in a city park. © 2015 IEEE.

Colla V.,Polytechnic University of Turin | Vannucci M.,TeCIP Institute | Reyneri L.M.,Polytechnic University of Turin
Intelligent Data Analysis | Year: 2014

The estimate of the probability density function or probability mass function of an unknown stochastic process is a very important preliminary step for any further elaboration. Most of the traditional approaches to this problem perform a preliminary choice of a parametric mathematical model of the function to estimate and a subsequent fitting on its parameters. To this aim some a-priori knowledge and/or assumptions on the phenomenon under consideration are needed. In this paper an alternative approach is proposed, which does not require any assumption on the available data, as it extracts the probability density function from the output of a neural network, that is trained with a suitable database including the original data and some ad hoc created data with known distribution. The results of the tests performed on synthetic and industrial databases are described and discussed in the paper. © 2015 - IOS Press and the authors. All rights reserved.

Cateni S.,TeCIP Institute | Colla V.,TeCIP Institute | Vannucci M.,TeCIP Institute | Vannocci M.,TeCIP Institute
IASTED Multiconferences - Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2013 | Year: 2013

Hardenability is an important property of steel, that is characterised through a curve known as Jominy profile. The paper presents a neural network-based approach to the prediction of this curve on the basis of steel chemical composition. The proposed approach is divided in two parts: firstly a set of neural networks is exploited for the sequential estimation of the points of the curve. Afterwards an additional network estimate the reliability of the profile prediction at each point. The model proved to be effective through tests on a real industrial dataset.

Leonardis D.,TeCIP Institute | Frisoli A.,TeCIP Institute | Barsotti M.,TeCIP Institute | Vanello N.,University of Pisa | Bergamasco M.,TeCIP Institute
Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics | Year: 2012

Motor imagery techniques are largely used in asynchronous BCI for the control of external devices. In this work we comparatively evaluate the performance of different state-of arts BCI algorithms, based on the Common Spatial Pattern approach, under different sensory feedback conditions. In particular the role of tendon vibration, inducing illusory movement, is analyzed in the context of BCI for motor imagery. © 2012 IEEE.

Vannucci M.,TeCIP Institute | Colla V.,TeCIP Institute | Dettori S.,TeCIP Institute
IFAC-PapersOnLine | Year: 2016

In the industrial and manufacturing field, many problems require the tuning of the parameters of complex empirical or theoretical models by means of the exploitation of data. In some cases the use of analytical methods for the determination of such parameters is not applicable, thus heuristic methods are employed. One of the main disadvantages of the use of these latter approaches is the risk of converging to a sub-optimal solution due to characteristics of the search surface which is determined both by the model and the data available for the tuning. In this paper the use of a novel type of genetic algorithms is proposed to overcome this drawback. This approach exploits a fuzzy inference system that controls the search strategies of the genetic algorithm on the basis of the real-time status of the optimization process. In this paper this method is tested on three problems drawn from the steel-making industry that put into evidence the improvement of the capability of avoiding the local minima of the optimization problem and the acceleration of the search process. © 2016

Dehkordi M.B.,TeCIP Institute | Frisoli A.,TeCIP Institute | Sotgiu E.,TeCIP Institute | Bergamasco M.,TeCIP Institute
International Journal of Advanced Robotic Systems | Year: 2012

This paper presents the modelling and experimental evaluation of the gravity compensation of a horizontal 3-UPU parallel mechanism. The conventional Newton-Euler method for static analysis and balancing of mechanisms works for serial robots; however, it can become computationally expensive when applied to the analysis of parallel manipulators. To overcome this difficulty, in this paper we propose an approach, based on a Lagrangian method, that is more efficient in terms of computation time. The derivation of the gravity compensation model is based on the analytical computation of the total potential energy of the system at each position of the end-effector. In order to satisfy the gravity compensation condition, the total potential energy of the system should remain constant for all of the manipulator's configurations. Analytical and mechanical gravity compensation is taken into account, and the set of conditions and the system of springs are defined. Finally, employing a virtual reality environment, some experiments are carried out and the reliability and feasibility of the proposed model are evaluated in the presence and absence of the elastic components. © 2012 Dehkordi et al.

Peppoloni L.,TeCIP Institute | Satler M.,TeCIP Institute | Luchetti E.,TeCIP Institute | Avizzano C.A.,TeCIP Institute | Tripicchio P.,TeCIP Institute
INES 2014 - IEEE 18th International Conference on Intelligent Engineering Systems, Proceedings | Year: 2014

The problem of object recognition and detection has been largely addressed by the robotics community, since its importance both in mapping and manipulation problems. One possible approach for the recognition task is to assume a specific a-priori knowledge of the objects possibly present in a scene. In this framework, this paper presents a novel technique for object detection and recognition based on Stacked Generalization (SG) method developed by Wolpert in 1992. The innovation of the proposed technique is the introduction of SG classification method to perform a multi-layer object recognition fusing heterogeneous spatial and color data acquired with an RGB-D camera. To improve the accuracy and the robustness of the system to environmental variability, we introduce a second layer classifier. Its goal is to evaluate and weights the results of the first layer classifiers, thus combining and improving the overall classification performance. This technique has a low computational cost and is suitable for on-line applications, such as robotic manipulation or automated logistic systems. To validate the presented approach experimental tests have been carried out and results are reported. © 2014 IEEE.

Peppoloni L.,Tecip Institute | Brizzi F.,Tecip Institute | Avizzano C.A.,Tecip Institute | Ruffaldi E.,Tecip Institute
2015 IEEE Symposium on 3D User Interfaces, 3DUI 2015 - Proceedings | Year: 2015

The development of natural interfaces for human-robot interaction provides the user an intuitive way to control and guide robots. In this paper, we propose a novel ROS (Robot Operating System)-integrated interface for remote control that allows the user to teleoperate the robot using his hands motion. The user can adjust online the autonomy of the robot between two levels: direct control and waypoint following. The hand tracking and gestures recognition capabilities of the Leap Motion device are exploited to generate the control commands. The user receives a real-time 3D augmented visual feedback using a Kinect sensor and a HMD. To assess the practicability of the system experimental results are presented using as a benchmark the remote control of a Kuka Youbot. © 2015 IEEE.

Rosati Papini G.P.,TeCIP Institute | Avizzano C.A.,TeCIP Institute
Proceedings - IEEE International Workshop on Robot and Human Interactive Communication | Year: 2012

The Body Extender is a whole-body exoskeleton designed to operate in unknown and difficult environments, for instance in disaster areas. The Body Extender allows the wearing operator to increase its force while maintaining a high level of perception. © 2012 IEEE.

Moretti G.,TeCIP Institute | Rosati G.P.P.,TeCIP Institute | Fontana M.,TeCIP Institute | Vertechy R.,University of Bologna
MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World | Year: 2015

This paper presents a small-scale test-bench that can be employed for the study of a new class of Oscillating Water Column (OWC) Wave Energy Converters (WECs) with Power Take Off (PTO) unit based on Dielectric Elastomer Generators (DEGs). Such a test-bench is designed to perform Hardware-In-the-Loop (HIL) simulations of a small-scale DEG PTO prototype, that includes dedicated power and control electronics, with a real-time model that emulates OWC plant hydrodynamics. The paper illustrates the theoretical model that is assumed to describe the dynamics of the OWC plant, the hardware employed to replicate the response of the DEG PTO and the algorithms for the implementation of the closed-loop controller that performs the HIL simulations. Some preliminary tests are reported considering a floating OWC collector and a simple energy-harvesting control law for the DEG PTO that is based on the measurement of the water level into the OWC structure. © 2015 IEEE.

Loading TeCIP Institute collaborators
Loading TeCIP Institute collaborators