IAS-LAB PUBLICATIONS
scopus.authority.anceserie||scopus.publisher.name||scopus.description.allpeopleoriginal||scopus.title
Authors: 14 HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY; eng 2-s2.0-84943232643
Journal: Italy||Italy||Italy||Italy||Italy||Italy||Italy||Italy||Italy||Italy
Published: false
Volume: Pagello E.; Menegatti E.; Bredenfeld A.; Costa P.; Christaller T.; Jacoff A.; Johnson J.; Riedmiller M.; Saffiotti A.; Tomoichi T. Pages: Pagello||Menegatti||Bredenfeld||Costa||Christaller||Jacoff||Johnson||Riedmiller||Saffiotti||Tomoichi
scopus.description.abstract||scopus.description.allpeopleoriginal||scopus.title
Authors: 98 445 BURGESS DRIVE, MENLO PK, CA 94025-3496 USA; eng 2-s2.0-3142721990
Journal: Italy||Italy||Germany||Portugal||United States||Germany||Germany||Sweden||United States||Japan
Published: 25
Volume: Pagello E.; Menegatti E.; Bredenfel A.; Costa P.; Christaller T.; Jacoff A.; Polani D.; Riedmiller M.; Saffiotti A.; Sklar E.; Tomoichi T. Pages: Pagello||Menegatti||Bredenfel||Costa||Christaller||Jacoff||Polani||Riedmiller||Saffiotti||Sklar||Tomoichi-This article reports on the RoboCup-2003 event. RoboCup is no longer just the Soccer World Cup for autonomous robots but has evolved to become a coordinated initiative encompassing four different robotics events: (1) Soccer, (2) Rescue, (3) Junior (focused on education), and (4) a Scientific Symposium. RoboCup-2003 took place from 2 to 11 July 2003 in Padua (Italy); it was colocated with other scientific events in the field of AI and robotics. In this article, in addition to reporting on the results of the games, we highlight the robotics and AI technologies exploited by the teams in the different leagues and describe the most meaningful scientific contributions. © 2004, American Association for Artificial Intelligence. All rights reserved.
scopus.relation.conferencename||scopus.relation.conferencedate||scopus.identifier.isbn||scopus.description.allpeopleoriginal||scopus.relation.conferenceplace
Authors: eng 2-s2.0-14044250905
Journal: Italy||Italy||Italy||Italy||Japan
Published: doi
Volume: Menegatti E.; Cicirelli G.; Simionato C.; D'Orazio T.; Ishiguro H. Pages: Menegatti||Cicirelli||Simionato||D'Orazio||Ishiguro-This paper presents an Omnidirectional Distributed Vision System that learns to navigate a robot in an office-like environment without any knowledge about the calibration of the cameras or the robot control law. The system is composed of several omnidirectional Vision Agents (implemented with an omnidirectional camera and a computer). The first Vision Agent learns to control the robot with SARSA(λ) reinforcement learning, using the LEM strategy to speed-up learning. Once the first Vision Agent learnt the correct policy, it transfers its knowledge to the other Vision Agents. The other Vision Agents might have different intrinsic and extrinsic camera parameters (that are unknown), so a certain amount of re-learning is needed. Reinforcement learning is well suited for this. In this paper, we present the structure of the learning system and the discussion about the optimal values for the learning parameters. During the experimentation the learning phase of the first agent has been carried out, then the knowledge propagation and the re-learning stage of three different agents have been tested. The experimental results demonstrate the feasibility of the approach and the possibility to port the system on the actual robot and cameras.
ERROR
Authors: AREA MIN. 09 - Ingegneria industriale e dell'informazione; Non assegn; ITA; 2015-06-05T03:19:24Z; 9781586034146
Published: MATCH_RESULT_STATUS_FAILURE_NO_MATCH
scopus.description.abstract||scopus.publisher.name||scopus.relation.lastpage||scopus.subject.keywords||scopus.relation.firstpage||scopus.description.allpeopleoriginal||scopus.identifier.doi
Authors: 283 125 London Wall, London, ENGLAND; eng 2-s2.0-0347915529
Journal: Italy||Italy||Italy||Italy||Italy||Italy||Italy||Italy
Published: Elsevier Ltd
Volume: Altavilla G.; Caputo A.; Trabanelli C.; Brocca Cofano E.; Sabbioni S.; Menegatti M.A.; Barbanti-Brodano G.; Corallini A. Pages: Altavilla||Caputo||Trabanelli||Brocca Cofano||Sabbioni||Menegatti||Barbanti-Brodano||Corallini-The human immunodeficiency virus type 1 (HIV-1) Tat protein stimulates cell proliferation, inhibits apoptosis, displays angiogenic functions and is believed to be involved in the pathogenesis of Kaposi's sarcoma (KS) and other tumours arising in AIDS patients. Tat-transgenic (TT) mice, which constitutively express Tat in all tissues and organs, may therefore be predisposed to tumorigenesis. To test this hypothesis, we treated TT mice with urethane, a general carcinogen inducing tumours of various organs. The results indicate that, after injection of urethane, the incidence of lung tumours and lymphomas is not significantly different in the TT and control (CC) mice, whereas liver preneoplastic lesions and tumours show a significantly greater incidence in TT than in CC mice. This remarkable carcinogenic effect of urethane for the liver may be due to a tat-induced predisposition, manifested as a liver cell dysplasia (LCD), spontaneously affecting most of the TT mice. LCD may exert a promoting effect by stimulating proliferation of cell clones initiated by the mutagenic effect of urethane. In addition, LCD, which is associated with aneuploidy and chromosome instability, may enhance the progression to malignancy of the preneoplastic lesions induced by urethane. Interestingly, a significantly greater incidence of vascular ectasias and haemangiomas was detected in the liver of urethane-treated TT mice, most likely due to the marked angiogenic properties of Tat. This study suggests a role for Tat in the promotion and progression of tumours initiated by exogenous and endogenous carcinogens in HIV-1-infected patients, thereby contributing to the tumorigenesis in the course of AIDS. © 2003 Elsevier Ltd. All rights reserved.
ERROR
Authors: AREA MIN. 09 - Ingegneria industriale e dell'informazione; Non assegn; 2015-06-05T04:36:32Z
Published: MATCH_RESULT_STATUS_FAILURE_NO_MATCH
W36965723
Authors: AREA MIN. 09 - Ingegneria industriale e dell'informazione; Non assegn; ITA; 2015-06-05T04:37:08Z; 9781586034146
Published: title_year
ERROR
Authors: AREA MIN. 09 - Ingegneria industriale e dell'informazione; Non assegn; ITA; 2015-06-05T03:44:34Z; 9788889422090
Published: MATCH_RESULT_STATUS_FAILURE_NO_MATCH
scopus.subject.keywords||scopus.description.allpeopleoriginal||scopus.description.abstract
Authors: 30 RADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS; eng 2-s2.0-3342937744
Journal: Italy||Italy||Italy||Japan
Published: false
DOI: University of Padua||University of Padua||CNR||Osaka University
Volume: Menegatti E.; Zoccarato M.; Pagello E.; Ishiguro H. Pages: Menegatti||Zoccarato||Pagello||Ishiguro-Monte Carlo localisation generally requires a metrical map of the environment to calculate a robots position from the posterior probability density of a set of weighted samples. Image-based localisation, which matches a robots current view of the environment with reference views, fails in environments with perceptual aliasing. The method we present in this paper is experimentally demonstrated to overcome these disadvantages in a large indoor environment by combining Monte Carlo and image-based localisation. It exploits the properties of the Fourier transform of omnidirectional images, while weighting the samples according to the similarity among images. We also introduce a novel strategy for solving the "kidnapped robot problem". © 2004 Elsevier B.V. All rights reserved.
scopus.subject.keywords||scopus.relation.article||scopus.relation.conferencedate||scopus.description.allpeopleoriginal||scopus.description.abstract||scopus.relation.conferencename||scopus.relation.conferenceplace||scopus.relation.volume
Authors: 441 345 E 47TH ST, NEW YORK, NY 10017 USA; eng 2-s2.0-33846615002
Journal: Italy||Italy||Italy
Published: doi
DOI: University of Trieste||University of Trieste||University of Padova
1573606
Volume: Mumolo E.; Nolich M.; Menegatti E. Pages: Mumolo||Nolich||Menegatti-In human heads there is a strong structural linkage between vocal tract and facial behavior during speech. For a robotic talking head to have a human-like behavior, this linkage should be emulated. One way to do that is to compute an estimate of the articulatory features which produce a given utterance and then to transform them into facial animation. We present a computational model of human vocalization which is aimed at describing the articulatory mechanisms which produce spoken phonemes. It uses a set of fuzzy rules and genetic optimization. The former represents the relationships between places of articulations and speech acoustic parameters, while the latter estimates the degrees of membership of the places of articulation. That is, the places of articulation are considered as fuzzy sets whose degrees of membership are the articulatory features. The trajectories of articulatory parameters can be used to control a graphical or mechanical talking head. We verify the model presented here by generating and listening to artificial sentences. Subjective listening tests of artificially generated sentences from the articulatory description resulted in an average phonetic accuracy of about 79 %. Through the analysis of a large amount of natural speech, the algorithm can be used to learn the places of articulation of all phonemes of a given speaker. ©2005 IEEE.