Organizational Unit:
Institute for Robotics and Intelligent Machines (IRIM)
Institute for Robotics and Intelligent Machines (IRIM)
Permanent Link
Research Organization Registry ID
Description
Previous Names
Parent Organization
Parent Organization
Includes Organization(s)
Organizational Unit
Organizational Unit
ArchiveSpace Name Record
7 results
Publication Search Results
Now showing
1 - 7 of 7
-
ItemDetecting region transitions for human-augmented mapping(Georgia Institute of Technology, 2010-08) Christensen, Henrik I. ; Topp, Elin A.In this paper, we describe a concise method for the feature-based representation of regions in an indoor environment and show how it can also be applied for door-passage-independent detection of transitions between regions to improve communication with a human user.
-
ItemDetecting structural ambiguities and transistions during a guided tour(Georgia Institute of Technology, 2008-05) Topp, Elin A. ; Christensen, Henrik I.Service robots designed for domestic settings need to navigate in an environment that they have to share with their users. Thus, they have to be able to report their current state and whereabouts in a way that is comprehensible for the user. Pure metric maps do not usually correspond to the understanding of the environment a user would provide. Thus, the robotic map needs to be integrated with the human representation. With our framework for Human Augmented Mapping we aim to deal with this issue and assume a guided tour as basis for an initial mapping process. During such a tour the robotic system needs to be able to detect significant changes in its environment representation – structural ambiguities – to be able to invoke a clarification discourse with the user. In this paper we present our approach to the detection of such ambiguities, that is independent from prior specification and training of particular spatial categories. We evaluate our method on data sets obtained during several runs in indoor environments in the context of a guided tour scenario.
-
ItemFrom sensors to human spatial concepts: An annotated data set(Georgia Institute of Technology, 2008-03) Zivkovic, Zoran ; Booij, Olaf ; Kröse, Ben ; Topp, Elin A. ; Christensen, Henrik I.An annotated data set is presented meant to help researchers in developing, evaluating, and comparing various approaches in robotics for building space representations appropriate for communicating with humans. The data consist of omnidirectional images, laser range scans, sonar readings, and robot odometry. A set of base-level human spatial concepts is used to annotate the data.
-
ItemBringing Together Human and Robotic Environment Representations – A Pilot Study(Georgia Institute of Technology, 2006-10) Topp, Elin A. ; Hüttenrauch, Helge ; Christensen, Henrik I. ; Eklundh, Kerstin SeverinsonHuman interaction with a service robot requires a shared representation of the environment for spoken dialogue and task specification where names used for particular locations are depending on personal preferences. A question is how such human oriented models can be tied to the geometric robotic models needed for precise localisation and navigation. We assume that this integration can be based on the information potential users give to a service robot about its working environment. We further believe that this information is best given in an interactive setting (a "guided tour") in this particular environment. This paper presents a pilot study that investigates how humans present a familiar environment to a mobile robot. The study is set up within our concept of Human Augmented Mapping, for which we assume an initial "guided tour" scenario to teach a robot its environment. Results from this pilot study are used to validate a proposed generic environment model for a service robot.
-
ItemTopological Modelling for Human Augmented Mapping(Georgia Institute of Technology, 2006-10) Topp, Elin A. ; Christensen, Henrik I.Service robots designed for domestic settings need to navigate in an environment that they have to share with their users. Thus, they have to be able to report their current state and whereabouts in a way that is comprehensible for the user. Pure metric maps do not usually correspond to the understanding of the environment a user would provide. Thus, the robotic map needs to be integrated with the human representation. This paper describes our framework of Human Augmented Mapping that allows us to achieve this integration.We propose further a method to specify and represent regions that relate to a user’s view on the environment. We assume an interactive setup for the specification of regions and show the applicability of our method in terms of distinctiveness for space segmentation and in terms of localisation purposes.
-
ItemWhat's in the gap? Interaction transitions that make HRI work(Georgia Institute of Technology, 2006-09) Hüttenrauch, Helge ; Eklundh, Kerstin Severinson ; Green, Anders ; Topp, Elin A. ; Christensen, Henrik I.This paper presents an in-depth analysis from a Human Robot Interaction (URI) study on spatial positioning and interaction episode transitions. Subjects showed a living room to a robot to teach it new places and objects. This joint task was analyzed with respect to organizing strategies for interaction episodes. Noticing the importance of transitions between interaction episodes, small adaptive movements in posture were observed. This finding needs to be incorporated into URI modules that plan and execute robots' spatial behavior in interaction, e.g., through dynamic adaptation of spatial formations and distances depending on interaction episode.
-
ItemAcquiring a shared environment representation(Georgia Institute of Technology, 2006) Topp, Elin A. ; Christensen, Henrik I. ; Eklundh, Kerstin SeverinsonInteracting with a domestic service robot implies the existence for a joint environment model for a user and a robot. We present a pilot study that investigates, how humans present a familiar environment to a mobile robot. Results from this study are used to evaluate a generic environment model for a service robot that can be personalised by interaction.