Organizational Unit:
Institute for Robotics and Intelligent Machines (IRIM)

Research Organization Registry ID
Description
Previous Names
Parent Organization
Parent Organization
Includes Organization(s)
Organizational Unit
ArchiveSpace Name Record

Publication Search Results

Now showing 1 - 9 of 9
  • Item
    Domestic robot ecology - an initial framework to unpack long-term acceptance of robots at home
    (Georgia Institute of Technology, 2010) Sung, Ja-Young ; Grinter, Rebecca E. ; Christensen, Henrik I.
    It has been recognized that long-term effects exist in the interaction with robotic technologies. Despite this recognition, we still know little about how the temporal effects are associated with domestic robots. To bridge this gap, we undertook a long-term field study. We distributed Roomba vacuuming robots to 30 households, and observed the use over six months. During this study, which spans over 149 home visits, we identified how householders accepted robots as a part of the households via four temporal stages of pre-adoption, adoption, adaptation, and use/retention. With these findings, we took the first step toward establishing a framework, Domestic Robot Ecology (DRE). It shows a holistic view on the relationships that robots shape in the home. Further, it articulates how those relationships change over time. We suggest that DRE can become a useful tool to help design toward long-term acceptance of robotic technologies in the home.
  • Item
    Pimp my Roomba: designing for personalization
    (Georgia Institute of Technology, 2009-04) Sung, Ja-Young ; Grinter, Rebecca E. ; Christensen, Henrik I.
    We present a study of how householders personalize their domestic vacuuming robot, iRobot's Roomba". In particular, we build on Blom and Monk's [3] theory of personalization that argues that personalization does not only occur naturally but can also be induced by design choices. In this study, we created a personalization toolkit, which allowed people to customize their Roomba's appearance and distributed it to 15 households. Our observations of these households provide empirical support that personalization can facilitate positive experiences with a Roomba, and having materials to hand can increase the odds of customization. We conclude by discussing design implications for personalization.
  • Item
    Sensing and estimation
    (Georgia Institute of Technology, 2008-05) Christensen, Henrik I. ; Hager, G.
  • Item
    Housewives or technophiles?: understanding domestic robot owners
    (Georgia Institute of Technology, 2008-03) Sung, Ja-Young ; Grinter, Rebecca E. ; Christensen, Henrik I. ; Guo, Lan
    Despite the growing body of Human-Robot Interaction (HRI) research focused on domestic robots, surprisingly little is known about the demographic profile of robot owners and their influence on usage patterns. In this paper, we present the results of a survey of 379 iRobot's Roombao wners, that identified their demographic and usage trends. The outcome of the survey suggests that Roomba users are equally likely to be men or women, and they tend to be younger with high levels of education and technical backgrounds. Their adoption and use patterns illustrate the important role that gift exchange plays in adoption, and how the robot changes cleaning routines and creates non-cleaning activities. More generally, we argue that domestic robot adoption is growing, and suggest some of the factors that lead to a positive experience.
  • Item
    Agent Negotiation of Target Distribution Enhancing System Survivability
    (Georgia Institute of Technology, 2007-12) Xiong, Ning ; Christensen, Henrik I. ; Svensson, Per
    This article proposes an agent negotiation model for target distribution across a set of geographically dispersed sensors. The key idea is to consider sensors as autonomous agents that negotiate over the division of tasks among them for obtaining better payoffs. The negotiation strategies for agents are established based upon the concept of subgame perfect equilibrium from game theory. Using such negotiation leads to not only superior measuring performance from a global perspective but also possibly balanced allocations of tasks to sensors, benefiting system robustness and survivability. A simulation test and results are given to demonstrate the ability of our approach in improving system security while keeping overall measuring performance near optimal.
  • Item
    My roomba is rambo: Intimate home appliances
    (Georgia Institute of Technology, 2007-09) Sung, Ja-Young ; Guo, Lan ; Grinter, Rebecca E. ; Christensen, Henrik I.
    Robots have entered our domestic lives, but yet, little is known about their impact on the home. This paper takes steps towards addressing this omission, by reporting results from an empirical study of iRobot’s Roomba™, a vacuuming robot. Our findings suggest that, by developing intimacy to the robot, our participants were able to derive increased pleasure from cleaning, and expended effort to fit Roomba into their homes, and shared it with others. These findings lead us to propose four design implications that we argue could increase people’s enthusiasm for smart home technologies.
  • Item
    Darwinian embodied evolution of the learning ability for survival
    (Georgia Institute of Technology, 2007) Elfwing, Stefan ; Uchibe, Eiji ; Doya, Kenji ; Christensen, Henrik I.
    In this article we propose a framework for performing embodied evolution with a limited number of robots, by utilizing time-sharing in subpopulations of virtual agents hosted in each robot. Within this framework, we explore the combination of within-generation learning of basic survival behaviors by reinforcement learning, and evolutionary adaptations over the generations of the basic behavior selection policy, the reward functions, and metaparameters for reinforcement learning. We apply a biologically inspired selection scheme, in which there is no explicit communication of the individuals' fitness information. The individuals can only reproduce offspring by mating—a pair-wise exchange of genotypes—and the probability that an individual reproduces offspring in its own subpopulation is dependent on the individual’s “health,” that is, energy level, at the mating occasion. We validate the proposed method by comparing it with evolution using standard centralized selection, in simulation, and by transferring the obtained solutions to hardware using two real robots.
  • Item
    Long-term study of portable field robots in urban terrain
    (Georgia Institute of Technology, 2006-08) Lundberg, Carl ; Christensen, Henrik I. ; Reinhold, Roger
  • Item
    Clarification dialogues in human-augmented mapping
    (Georgia Institute of Technology, 2006-03) Kruijff, Geert-Jan M. ; Zender, Hendrik ; Jensfelt, Patric ; Christensen, Henrik I.
    An approach to dialogue based interaction for resolution of ambiguities encountered as part of Human-Augmented Mapping (HAM) is presented. The paper focuses on issues related to spatial organisation and localisation. The dialogue pattern naturally arises as robots are introduced to novel environments. The paper discusses an approach based on the notion of Questions under Discussion (QUD). The presented approach has been implemented on a mobile platform that has dialogue capabilities and methods for metric SLAM. Experimental results from a pilot study clearly demonstrate that the system can resolve problematic situations.