Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Agnes Swadzba"'
Autor:
Agnes Swadzba, Sebastian Wrede, Christian Emmerich, Ricarda Grünberg, Arne Nordmann, Jochen J. Steil
Publikováno v:
Journal of Human-Robot Interaction. 2:56-81
The recent advent of compliant and kinematically redundant robots poses new research challenges for human-robot interaction. While these robots provide a great degree of flexibility for the realization of complex applications, the flexibility gained
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f36dd1cc246d78f958f750bf0b12598
https://doi.org/10.5898/jhri.2.1.wrede
https://doi.org/10.5898/jhri.2.1.wrede
Autor:
Agnes Swadzba, Sebastian Wrede, Arne Nordmann, Christian Emmerich, Ricarda Grünberg, Jochen J. Steil
Publikováno v:
Springer Tracts in Advanced Robotics ISBN: 9783319038377
Springer Tracts in Advanced Robotics ISBN: 9783319029337
Springer Tracts in Advanced Robotics ISBN: 9783319029337
The presented work approaches programming of redundant robots such as the KUKA Lightweight Robot IV in a co-worker scenario from a user-centered point of view. It specifically asks, how the user’s implicit knowledge about the scene and the task can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::221b46af1cad67b6437de6c125bd6417
https://doi.org/10.1007/978-3-319-03838-4_6
https://doi.org/10.1007/978-3-319-03838-4_6
Autor:
Agnes Swadzba, Sven Wachsmuth
Enhancing perception of the local environment with semantic information like the room type is an important ability for agents acting in their environment. Such high-level knowledge can reduce the effort needed for, for example, object detection. This
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::611ca671d15348fdd47501847679dd79
https://pub.uni-bielefeld.de/record/2563576
https://pub.uni-bielefeld.de/record/2563576
Publikováno v:
3DV
The recognition of object categories in 3D scenes is still a challenging problem in computer vision. Many state of the art approaches use Implicit Shape Models, as addressed in [8] and [14], to learn shapes of object categories and a probabilistic Ho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4cee7944af4563f5d1472b97669c131f
https://doi.org/10.1109/3dv.2013.55
https://doi.org/10.1109/3dv.2013.55
Publikováno v:
PUB-Publications at Bielefeld University
BASE-Bielefeld Academic Search Engine
ICRA
BASE-Bielefeld Academic Search Engine
ICRA
Facilitating efficient reconfiguration of advanced robot systems to new tasks or environments is an ongoing research challenge. While imitation learning methods as well as modeling and simulation tools are continuously improving to reduce the inheren
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::077844aee0fdad6604709ee34cb73b5a
https://pub.uni-bielefeld.de/record/2549946
https://pub.uni-bielefeld.de/record/2549946
Publikováno v:
Spatial Information Theory ISBN: 9783319017891
COSIT
COSIT
Automatic generation of adequate spatial relations with regard to reference object selection is a nontrivial problem. In the present paper, we develop, implement and evaluate a computational model for reference object selection using empirically deri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1b900c12750ee08db3046c797603a5a0
https://doi.org/10.1007/978-3-319-01790-7_20
https://doi.org/10.1007/978-3-319-01790-7_20
The reliable automatic visual recognition of indoor scenes with complex object constellations using only sensor data is a nontrivial problem. In order to improve the construction of an accurate semantic 3D model of an indoor scene, we exploit human-p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b9d3e62d05192e277cc14d5035e6728f
https://doi.org/10.1007/s10339-012-0460-1
https://doi.org/10.1007/s10339-012-0460-1
Autor:
Sven Wachsmuth, Agnes Swadzba
Publikováno v:
Computer Vision – ACCV 2010 ISBN: 9783642193088
ACCV (2)
ACCV (2)
Scene categorization is an important mechanism for providing high-level context which can guide methods for a more detailed analysis of scenes. State-of-the-art techniques like Torralba's Gist features show a good performance on categorizing outdoor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9e808a7788b4f04355e1e0e2ada5c0d1
https://pub.uni-bielefeld.de/record/2034745
https://pub.uni-bielefeld.de/record/2034745
Publikováno v:
ICRA
In this paper we present a new system for a mobile robot to generate an articulated scene model by analyzing complex dynamic 3D scenes. The system extracts essential knowledge about the foreground, like moving persons, and the background, which consi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11d8dd8607c152d2ff5426b54b3d70ea
https://doi.org/10.1109/robot.2010.5509225
https://doi.org/10.1109/robot.2010.5509225
In this paper we describe an efficient but detailed new approach to analyze complex dynamic scenes directly in 3D. The arising information is important for mobile robots to solve tasks in the area of household robotics. In our work a mobile robot bui
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::beb7845b9f0a86843a6b374084632a3d
https://doi.org/10.1007/3dres.03(2010)04
https://doi.org/10.1007/3dres.03(2010)04