Documents disponibles dans la sous-collection

Neural network perception for mobile robot guidance / Pomerleau, Dean A.

Public ISBD Titre : Neural network perception for mobile robot guidance Type de document : texte imprimé Auteurs : Pomerleau, Dean A., Auteur Editeur : Boston : Kluwer academic publishers Année de publication : 1993 Collection : The kluwer international series in engineering and computer science Sous-collection : Robotics: vision, manipulation and sensors num. 239 Importance : XIV-191p. Présentation : ill. Format : 24 cm ISBN/ISSN/EAN : 978-0-7923-9373-3 Note générale : Bibliogr. p.[179]-186. Index. Langues : Anglais (eng) Mots-clés : Mobile  robots Neural  networks  (Computer  science) Robots  --  Control  systems Commande  automatique Intelligence  artificielle Robotique Robots  mobiles Réseaux  neuronaux  (informatique) Index. décimale : 62-52 Machine et processus conduits ou contrôlés automatiquement Résumé : Vision based mobile robot guidance has proven difficult for classical machine vision methods because of the diversity and real time constraints inherent in the task. This book describes a connectionist system called ALVINN (Autonomous Land Vehicle In a Neural Network) that overcomes these difficulties. ALVINN learns to guide mobile robots using the back-propagation training algorithm. Because of its ability to learn from example, ALVINN can adapt to new situations and therefore cope with the diversity of the autonomous navigation task. But real world problems like vision based mobile robot guidance present a different set of challenges for the connectionist paradigm. Among them are: how to develop a general representation from a limited amount of real training data, how to understand the internal representations developed by artificial neural networks, how to estimate the reliability of individual networks, how to combine multiple networks trained for different situations into a single system, and how to combine connectionist perception with symbolic reasoning. Neural Network Perception for Mobile Robot Guidance presents novel solutions to each of these problems. Using these techniques, the ALVINN system can learn to control an autonomous van in under 5 minutes by watching a person drive. Once trained, individual ALVINN networks can drive in a variety of circumstances, including single-lane paved and unpaved roads, and multi-lane lined and unlined roads, at speeds of up to 55 miles per hour. The techniques also are shown to generalize to the task of controlling the precise foot placement of a walking robot. Note de contenu : Contents: * Network Architecture. * Training Networks "On-The-Fly". * Training Networks With Structured Noise. * Driving Results and Performance. * Analysis of Network Representations. * Rule-Based Multi-network Arbitration. * Output Appearance Reliability Estimation. * Input Reconstruction Reliability Estimation. * Other Applications. The SM[superscript 2]. * Other Vision-based Robot Guidance Methods. Neural network perception for mobile robot guidance [texte imprimé] / Pomerleau, Dean A., Auteur . - Kluwer academic publishers, 1993 . - XIV-191p. : ill. ; 24 cm. - (The kluwer international series in engineering and computer science. Robotics: vision, manipulation and sensors; 239) . ISBN : 978-0-7923-9373-3 Bibliogr. p.[179]-186. Index. Langues : Anglais (eng) Mots-clés : Mobile  robots Neural  networks  (Computer  science) Robots  --  Control  systems Commande  automatique Intelligence  artificielle Robotique Robots  mobiles Réseaux  neuronaux  (informatique) Index. décimale : 62-52 Machine et processus conduits ou contrôlés automatiquement Résumé : Vision based mobile robot guidance has proven difficult for classical machine vision methods because of the diversity and real time constraints inherent in the task. This book describes a connectionist system called ALVINN (Autonomous Land Vehicle In a Neural Network) that overcomes these difficulties. ALVINN learns to guide mobile robots using the back-propagation training algorithm. Because of its ability to learn from example, ALVINN can adapt to new situations and therefore cope with the diversity of the autonomous navigation task. But real world problems like vision based mobile robot guidance present a different set of challenges for the connectionist paradigm. Among them are: how to develop a general representation from a limited amount of real training data, how to understand the internal representations developed by artificial neural networks, how to estimate the reliability of individual networks, how to combine multiple networks trained for different situations into a single system, and how to combine connectionist perception with symbolic reasoning. Neural Network Perception for Mobile Robot Guidance presents novel solutions to each of these problems. Using these techniques, the ALVINN system can learn to control an autonomous van in under 5 minutes by watching a person drive. Once trained, individual ALVINN networks can drive in a variety of circumstances, including single-lane paved and unpaved roads, and multi-lane lined and unlined roads, at speeds of up to 55 miles per hour. The techniques also are shown to generalize to the task of controlling the precise foot placement of a walking robot. Note de contenu : Contents: * Network Architecture. * Training Networks "On-The-Fly". * Training Networks With Structured Noise. * Driving Results and Performance. * Analysis of Network Representations. * Rule-Based Multi-network Arbitration. * Output Appearance Reliability Estimation. * Input Reconstruction Reliability Estimation. * Other Applications. The SM[superscript 2]. * Other Vision-based Robot Guidance Methods.

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	Etat_Exemplaire
041556	62-52 POM	Papier	Bibliothèque Centrale	Automatique	Disponible

Qualitative motion understanding / Wilhelm Burger

Public ISBD Titre : Qualitative motion understanding Type de document : texte imprimé Auteurs : Wilhelm Burger, Auteur ; Bir Bhanu, Auteur Editeur : Boston : Kluwer academic publishers Année de publication : 1992 Collection : The kluwer international series in engineering and computer science Sous-collection : Robotics: vision, manipulation and sensors num. 184 Importance : XIII-210 p. Présentation : ill. Format : 24 cm ISBN/ISSN/EAN : 978-0-7923-9251-4 Note générale : Bibliogr. p. [199]-206. Index Langues : Anglais (eng) Mots-clés : Robots  --  Motion Computer  vision Artificial  intelligence Index. décimale : 62-52 Machine et processus conduits ou contrôlés automatiquement Résumé : Qualitative motion understanding describes a qualitative approach to dynamic scene and motion analysis, called DRIVE (Dynamic Reasoning from Integrated Visual Evidence). The DRIVE system addresses the observed 3-D scene structure, and (c) evaluating the motion of individual objects from a sequence of monocular images. The approach is based on the FOE (focus of expansion) concept but it takes a somewhat unconventional route. The DRIVE system uses a qualitative scene model and a fuzzy focus of expansion to estimate robot motion from visual cues, to detect and track moving objects, and to construct and maintain a global dynamic reference model. Note de contenu : Contents: * Framework for qualitative motion understanding. * Effects of camera motion. * Decomposing image motion. * The fueey foe. * Reasoning about structure and motion. * The qualitative scene model. * Examples. Qualitative motion understanding [texte imprimé] / Wilhelm Burger, Auteur ; Bir Bhanu, Auteur . - Kluwer academic publishers, 1992 . - XIII-210 p. : ill. ; 24 cm. - (The kluwer international series in engineering and computer science. Robotics: vision, manipulation and sensors; 184) . ISBN : 978-0-7923-9251-4 Bibliogr. p. [199]-206. Index Langues : Anglais (eng) Mots-clés : Robots  --  Motion Computer  vision Artificial  intelligence Index. décimale : 62-52 Machine et processus conduits ou contrôlés automatiquement Résumé : Qualitative motion understanding describes a qualitative approach to dynamic scene and motion analysis, called DRIVE (Dynamic Reasoning from Integrated Visual Evidence). The DRIVE system addresses the observed 3-D scene structure, and (c) evaluating the motion of individual objects from a sequence of monocular images. The approach is based on the FOE (focus of expansion) concept but it takes a somewhat unconventional route. The DRIVE system uses a qualitative scene model and a fuzzy focus of expansion to estimate robot motion from visual cues, to detect and track moving objects, and to construct and maintain a global dynamic reference model. Note de contenu : Contents: * Framework for qualitative motion understanding. * Effects of camera motion. * Decomposing image motion. * The fueey foe. * Reasoning about structure and motion. * The qualitative scene model. * Examples.

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	Etat_Exemplaire
041502	62-52 BUR	Papier	Bibliothèque Centrale	Automatique	Disponible

Efficient dynamic simulation of robotic mechanisms / Kathryn W. Lilly

Public ISBD Titre : Efficient dynamic simulation of robotic mechanisms Type de document : texte imprimé Auteurs : Kathryn W. Lilly, Auteur Editeur : Boston : Kluwer academic publishers Année de publication : 1993 Collection : The kluwer international series in engineering and computer science Sous-collection : Robotics: vision, manipulation and sensors num. 203 Importance : 136 p. Présentation : ill. Format : 24 cm ISBN/ISSN/EAN : 978-0-7923-9286-6 Note générale : Bibliogr. p. 129-132. Index Langues : Anglais (eng) Mots-clés : Robots  --  Dynamics  --  Mathematical  models Robots  --  Computer  simulation Commande  automatique Robots  industriels Index. décimale : 62-52 Machine et processus conduits ou contrôlés automatiquement Résumé : Presents computationally efficient algorithms for the dynamic simulation of closed-chain robotic systems. This work investigates in particular, the simulation of single closed chains and simple closed-chain mechanisms. In addition to computational efficiency, it retains as much physical insight as possible during algorithm derivation. Note de contenu : Contents: * System Modeling and Notation. * Alternate Formulations for the Joint Inertia Matrix. * Alternate Formulations for the Operational Space Inertia Matrix. * Efficient Dynamic Simulation of a Single Closed Chain. * Efficient Dynamic Simulation of Simple Closed-Chain Mechanisms. Efficient dynamic simulation of robotic mechanisms [texte imprimé] / Kathryn W. Lilly, Auteur . - Kluwer academic publishers, 1993 . - 136 p. : ill. ; 24 cm. - (The kluwer international series in engineering and computer science. Robotics: vision, manipulation and sensors; 203) . ISBN : 978-0-7923-9286-6 Bibliogr. p. 129-132. Index Langues : Anglais (eng) Mots-clés : Robots  --  Dynamics  --  Mathematical  models Robots  --  Computer  simulation Commande  automatique Robots  industriels Index. décimale : 62-52 Machine et processus conduits ou contrôlés automatiquement Résumé : Presents computationally efficient algorithms for the dynamic simulation of closed-chain robotic systems. This work investigates in particular, the simulation of single closed chains and simple closed-chain mechanisms. In addition to computational efficiency, it retains as much physical insight as possible during algorithm derivation. Note de contenu : Contents: * System Modeling and Notation. * Alternate Formulations for the Joint Inertia Matrix. * Alternate Formulations for the Operational Space Inertia Matrix. * Efficient Dynamic Simulation of a Single Closed Chain. * Efficient Dynamic Simulation of Simple Closed-Chain Mechanisms.

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	Etat_Exemplaire
041525	62-52 LIL	Papier	Bibliothèque Centrale	Automatique	Disponible

Bayesian modeling of uncertainty in low-level vision / Richard Szeliski

Public ISBD Titre : Bayesian modeling of uncertainty in low-level vision Type de document : texte imprimé Auteurs : Richard Szeliski, Auteur ; Takeo Kanade, Préfacier, etc. Editeur : Boston : Kluwer academic publishers Année de publication : 1989 Collection : The kluwer international series in engineering and computer science Sous-collection : Robotics: vision, manipulation and sensors num. 79 Importance : XVII-198 p. Présentation : ill. Format : 24 cm ISBN/ISSN/EAN : 978-0-7923-9039-8 Note générale : Index Langues : Anglais (eng) Mots-clés : Théorème  de  Bayes Perception  visuelle Algorithmes Computer  vision  --  Mathematical  models Vision  par  ordinateur  --  Modèles  mathématiques Index. décimale : 621.391 Notions générales sur l'ingénierie des Communications électriques.Cybernétique.Théorie de l'information.Théorie des signaux Résumé : Bayesian modeling of uncertainty in low-level vision develops a probablistic model for low-level vision problems such as surface interpolation and depth from motion. The model allows us to describe the uncertainty in the output of low-level vision algorithms. This uncertainty is inherent in all vision applications because of the noisy nature of real sensors. Modeling of this uncertainty allows us to create algorithms that are more robust with respect to this noise. Note de contenu : Contents: * Introduction. * Representations for low-level vision. * Bayesian models and Markov Random Fields. * Prior models. * Sensor models. * Posterior estimates. ... Bayesian modeling of uncertainty in low-level vision [texte imprimé] / Richard Szeliski, Auteur ; Takeo Kanade, Préfacier, etc. . - Kluwer academic publishers, 1989 . - XVII-198 p. : ill. ; 24 cm. - (The kluwer international series in engineering and computer science. Robotics: vision, manipulation and sensors; 79) . ISBN : 978-0-7923-9039-8 Index Langues : Anglais (eng) Mots-clés : Théorème  de  Bayes Perception  visuelle Algorithmes Computer  vision  --  Mathematical  models Vision  par  ordinateur  --  Modèles  mathématiques Index. décimale : 621.391 Notions générales sur l'ingénierie des Communications électriques.Cybernétique.Théorie de l'information.Théorie des signaux Résumé : Bayesian modeling of uncertainty in low-level vision develops a probablistic model for low-level vision problems such as surface interpolation and depth from motion. The model allows us to describe the uncertainty in the output of low-level vision algorithms. This uncertainty is inherent in all vision applications because of the noisy nature of real sensors. Modeling of this uncertainty allows us to create algorithms that are more robust with respect to this noise. Note de contenu : Contents: * Introduction. * Representations for low-level vision. * Bayesian models and Markov Random Fields. * Prior models. * Sensor models. * Posterior estimates. ...

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	Etat_Exemplaire
041567	621.391 SZE	Papier	Bibliothèque Centrale	Electronique	Disponible	En bon état

Measurement of image velocity / David J. Fleet

Public ISBD Titre : Measurement of image velocity Type de document : texte imprimé Auteurs : David J. Fleet, Auteur ; D. Jepson Allan, Préfacier, etc. Editeur : Boston : Kluwer academic publishers Année de publication : 1992 Collection : The kluwer international series in engineering and computer science Sous-collection : Robotics: vision, manipulation and sensors num. 169 Importance : XIII-203 p. Présentation : ill. Format : 24 cm ISBN/ISSN/EAN : 978-0-7923-9198-2 Note générale : Bibliogr. p. 111-200. Index Langues : Anglais (eng) Mots-clés : Computer  vision Image  processing Motion Measurement Index. décimale : 621.397 Technologie vidéo. Ingénierie de la télévision. Enregistrement vidéo, transmission et reproduction. Equipement et réseaux vidéo Résumé : Presents a computational framework for computing motion information from sequences of images. Its specific goal is the measurement of image velocity (or optical flow), the projection of 3-D object motion onto the 2-D image plane. Note de contenu : Contents: * Background. * Phase-Based Velocity Measurement. * On Phase Properties of Band-Pass Signals. * Conclusions. Measurement of image velocity [texte imprimé] / David J. Fleet, Auteur ; D. Jepson Allan, Préfacier, etc. . - Kluwer academic publishers, 1992 . - XIII-203 p. : ill. ; 24 cm. - (The kluwer international series in engineering and computer science. Robotics: vision, manipulation and sensors; 169) . ISBN : 978-0-7923-9198-2 Bibliogr. p. 111-200. Index Langues : Anglais (eng) Mots-clés : Computer  vision Image  processing Motion Measurement Index. décimale : 621.397 Technologie vidéo. Ingénierie de la télévision. Enregistrement vidéo, transmission et reproduction. Equipement et réseaux vidéo Résumé : Presents a computational framework for computing motion information from sequences of images. Its specific goal is the measurement of image velocity (or optical flow), the projection of 3-D object motion onto the 2-D image plane. Note de contenu : Contents: * Background. * Phase-Based Velocity Measurement. * On Phase Properties of Band-Pass Signals. * Conclusions.

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	Etat_Exemplaire
041603	621.397 FLE	Papier	Bibliothèque Centrale	Electronique	Disponible

Task-directed sensor fusion and planning / Gregory D. Hager

Permalink

Computer analysis of visual textures / Tomita , Fumiaki

Permalink

Control of machines with friction / Armstrong-Hélouvry, Brian

Permalink

Robotic object recognition using vision and touch / Peter K. Allen

Permalink

Intelligent robotic systems / Kimon P. Valavanis

Permalink

Vision and navigation

Permalink

Parallel architectures and parallel algorithms for integrated vision systems / Alok N. Choudhary

Permalink

Space robotics

Permalink

Intelligent robotic systems for space exploration

Permalink

A pyramid framework for early vision / Jean-Michel Jolion

Permalink