• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher:
    
    • McClelland, James L. (5)
    • Rumelhart, David E. (5)
    • Kochendörfer, Günter (4)
    • Alippi, Cesare (2)
    • Anderson, James A. (2)
    • Bechtel, William (2)
    • Chollet, Gérard (2)
    • Esposito, Anna (2)
    • Hussain, Amir (2)
    • Liu, Derong (2)
    •   more
  • 
    Year
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access:
    • free (69)
    • subject to license (0)

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Page: 1 2 3 4 Hits 1 – 20 of 69 1 Analysis of New Advances in the Application of Artificial Intelligence to Education Han, Lufeng In: Advances in Social Science, Education and Humanities Research ; 220 ; 608-611 (2020) BASE Show details 2 Natural language processing with PyTorch : build intelligent language applications using deep learning McMahan, Brian; Rao, Delip. - Tokyo : O'Reilly, 2019 BLLDB UB Frankfurt Linguistik Show details 3 How models of canonical microcircuits implement cognitive functions Kunze, Tim. - 2019 BASE Show details 4 Leveraging sparse and dense features for reliable state estimation in urban environments Radwan, Noha. - 2019 Abstract: An ultimate goal of mobile robotics research is the development of intelligent platforms that are capable of undertaking a variety of tasks in everyday life for their users. Over the previous decade, robots have become more integrated into our daily lives, performing tasks in numerous environments including industrial settings such as assembly and manufacturing, indoor scenes such as home assistance and educational tasks, and outdoor areas such as lawn mowing and parcel delivery. Despite the significant strides achieved in the various application areas, reliably deploying robots in urban environments remains an open challenge. In order to realize the goal of ubiquitous robotics, the ability of mobile robots to reliably estimate their state as well as the state of the agents in their vicinity is crucial for their successful deployment. However, in order to achieve this goal, robots need to overcome several challenges. The choice of sensor modality employed for extracting information about the environment plays a major role in the representational capabilities of the localization module. While LiDAR sensors are able to provide geometric information of the environment, cameras provide a low cost alternative with rich color and texture information which is crucial for reasoning about the scene. However, accurately estimating the pose of the robot using only cameras is an arduous task especially in urban scenarios. The complex nature of urban environments due to the presence of multiple repetitive structures and glass facades of buildings render the task of reliable localization extremely challenging. Furthermore, the varying weather and illumination conditions in addition to the frequently changing nature of the scene due to constructions necessitates the constant maintenance of the localization module to enable accurate state estimation. Urban environments commonly are of a highly dynamic and stochastic nature caused by moving pedestrians, cars and cyclists. Each of these agents often traverses a different trajectory and obeys different traffic rules. This in turn makes the task of estimating the state of surrounding agents extremely challenging. The aforementioned challenges render highly accurate generalizable hand-crafted solutions to the state estimation problem unattainable, as it is infeasible for an expert to anticipate and pre-program solutions for all potential scenarios. A promising solution for this problem is robots that are able to leverage the abundant rich information in the environment such as semantic, structural and geometric information in order to learn models for reliable and accurate state estimation. In this thesis, we address the problem of reliable state estimation in urban environments by introducing novel techniques that address these challenges through exploiting sparse and dense features of the scene. Inspired by how humans describe their location in urban cities, we propose a visual localization method that leverages the textual information in the scene to estimate the location of the robot by utilizing publicly available maps. This enables our method to achieve global scale breadth and low bandwidth requirements. We employ distance and linguistic-based metrics to probabilistically associate stable text from the environment with landmarks in the map. Our proposed method is the first to utilize textual information from the scene to produce reliable position estimates. In order to enable accurate pose estimation in the absence of textual information, we propose a multitask visual localization method that leverages the inter-task similarities between localization, ego-motion estimation and semantic scene segmentation for the mutual benefit of each of these tasks. Incorporating geometric and semantic constraints into our network enables the prediction of accurate pose estimates that are geometrically consistent with the robot motion, while being tolerant to perceptual aliasing and adverse illumination conditions. Finally, we propose a multimodal interaction-aware behavior prediction method for predicting the safety of street intersections for crossing during a given time interval. Our contribution goes beyond existing behavior prediction approaches by leveraging the interaction interdependencies between the various traffic participants to simultaneously predict an accurate future trajectory for each participant. Furthermore, by utilizing the predicted motions along with recognizing the traffic light signal, our model can estimate the safety of a street intersection for crossing while being invariant to the type of intersection. We present extensive experimental evaluations on several benchmarks as well as real-world datasets and show the effectiveness of our proposed methods in reliably estimating the state of the robot and all observable agents in its vicinity. Moreover, we provide thorough empirical evidence that demonstrates the generalization ability and robustness of our methods to different environments and challenging perceptual conditions, thus paving the way towards the reliable life-long deployment of robots that can autonomously navigate in our complex cities. Keyword: Bildsegmentierung; Deep learning; Künstliche Intelligenz; Lokalisation; Maschinelles Lernen; Maschinelles Sehen; Mustererkennung; Neuronales Netz; Robotik URL: https://freidok.uni-freiburg.de/data/149856 https://nbn-resolving.org/urn:nbn:de:bsz:25-freidok-1498567 https://doi.org/10.6094/UNIFR/149856 https://www.freidok.uni-freiburg.de/dnb/download/149856 BASE Hide details 5 Automatic speech recognition for low-resource languages and accents using multilingual and crosslingual information Vu, Ngoc Thang. - Aachen : Shaker, 2014 BLLDB UB Frankfurt Linguistik Show details 6 Sentences in sentences : modeling frequency effects in local syntactic coherence processing ; Sätze in Sätzen : Modellierung von Frequenzeffekten bei der Verarbeitung lokaler syntaktischer Kohärenz Müller-Feldmeth, Daniel Georg. - : Albert-Ludwigs-Universität Freiburg, 2014 BASE Show details 7 Advances in Brain Inspired Cognitive Systems : 6th International Conference, BICS 2013, Beijing, China, June 9-11, 2013. Proceedings Liu, Derong; Alippi, Cesare; Zhao, Dongbin. - Berlin, Heidelberg : Springer Berlin Heidelberg, 2013 UB Frankfurt Linguistik Show details 8 Verstehensprozesse modellieren und analysieren Braun, Gregor. - Berlin : Frank & Timme, 2013 IDS Mannheim Show details 9 Advances in brain inspired cognitive systems : 6th international conference ; proceedings Liu, Derong (Hrsg.); Alippi, Cesare (Hrsg.); Zhao, Dongbin (Hrsg.). - Heidelberg [u.a.] : Springer, 2013 UB Frankfurt Linguistik Show details 10 Konnektionistische Methoden in der prosodischen Analyse und Generierung Jokisch, Oliver. - Dresden : TUDpress, 2011 BLLDB UB Frankfurt Linguistik Show details 11 Polyglot text to speech synthesis : text analysis & prosody control Romsdorfer, Harald. - Aachen : Shaker, 2009 BLLDB UB Frankfurt Linguistik Show details 12 Sprache und Denken in neuronalen Netzen Hilberg, Wolfgang. - [Groß-Bieberau] : Sprache und Technik, 2008 BLLDB UB Frankfurt Linguistik Show details 13 Brain, meaning, and computation ; Gehirn, Bedeutung, und Computation Klein, Michael. - 2007 BASE Show details 14 Prosody recognition in speech dialogue systems : robust natural language understanding through prediction of semantic items by pattern recognition on nonverbal acoustic speech characteristics Quast, Holger. - Göttingen : Sierke, 2006 UB Frankfurt Linguistik Show details 15 Nonlinear Speech Modeling and Applications : Advanced Lectures and Revised Selected Papers Chollet, Gerard; Esposito, Anna; Faundez-Zanuy, Marcos. - Berlin, Heidelberg : Springer Berlin Heidelberg, 2005 UB Frankfurt Linguistik Show details 16 Nonlinear speech modeling and applications : advanced lectures and revised selected papers Chollet, Gérard (Hrsg.). - Berlin [u.a.] : Springer, 2005 UB Frankfurt Linguistik Show details 17 Phonetische Transkription für ein multilinguales Sprachsynthesesystem Hain, Horst-Udo. - Dresden : w.e.b.-Univ.-Verl., 2005 UB Frankfurt Linguistik Show details 18 Case-based reasoning with neuronal networks : from pixel via experiences to reasoning Klukas, Jörg. - Aachen : Shaker, 2004 BLLDB UB Frankfurt Linguistik Show details 19 Discriminative connectionist approaches for automatic speech recognition in cars Marí Hilario, Joan. - 2004 UB Frankfurt Linguistik Show details 20 The handbook of brain theory and neural networks Arbib, Michael A. (Hrsg.). - Cambridge, Mass. [u.a.] : MIT Press, 2003 UB Frankfurt Linguistik Show details Page: 1 2 3 4

Mobile view All Catalogues UB Frankfurt Linguistik 52 IDS Mannheim 10 OLC Linguistik 1 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 Institut für Empirische Sprachwissenschaft 2 Leibniz-Centre General Linguistics (ZAS) 1 Bibliographies BLLDB 31 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 0 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 6 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0