Now showing items 314-333 of 1552

    • Darwinian embodied evolution of the learning ability for survival 

      Elfwing, Stefan; Uchibe, Eiji; Doya, Kenji; Christensen, Henrik (Georgia Institute of TechnologySageInternational Society for Adaptive Behavior, 2007)
      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 ...
    • Data Driven MCMC for Appearance-based Topological Mapping 

      Dellaert, Frank; Ranganathan, Ananth (Georgia Institute of Technology, 2005)
      Probabilistic techniques have become the mainstay of robotic mapping, particularly for generating metric maps. In previous work, we have presented a hitherto nonexistent general purpose probabilistic framework for dealing ...
    • Data Driven MCMC for Appearance-Based Topological Mapping 

      Ranganathan, Ananth; Dellaert, Frank (Georgia Institute of TechnologyMIT Press, 2005)
      Probabilistic techniques have become the mainstay of robotic mapping, particularly for generating metric maps. In previous work, we have presented a hitherto nonexistent general purpose probabilistic framework for dealing ...
    • Data-Driven Generation of Low-Complexity Control Programs 

      Delmotte, Florent; Egerstedt, Magnus B.; Austin, Adam (Georgia Institute of TechnologyNonpareil Publishers, 2004)
      In this paper we study the problem of generating control programs, i.e. strings of symbolic descriptions of control-interrupt pairs (or modes) from input-output data. In particular, we take the point of view that such ...
    • Data-Driven MCMC for Learning and Inference in Switching Linear Dynamic Systems 

      Oh, Sang Min; Rehg, James M.; Balch, Tucker; Dellaert, Frank (Georgia Institute of TechnologyAAAI Press, 2005-07)
      Switching Linear Dynamic System (SLDS) models are a popular technique for modeling complex nonlinear dynamic systems. An SLDS has significantly more descriptive power than an HMM, but inference in SLDS models ...
    • DDF-SAM 2.0: Consistent Distributed Smoothing and Mapping 

      Cunningham, Alexander; Indelman, Vadim; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-05)
      This paper presents an consistent decentralized data fusion approach for robust multi-robot SLAM in dan- gerous, unknown environments. The DDF-SAM 2.0 approach extends our previous work by combining local and neigh- borhood ...
    • DDF-SAM: Fully Distributed SLAM using Constrained Factor Graphs 

      Cunningham, Alexander; Paluri, Manohar; Dellaert, Frank (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2010)
      We address the problem of multi-robot distributed SLAM with an extended Smoothing and Mapping (SAM) approach to implement Decentralized Data Fusion (DDF). We present DDF-SAM, a novel method for efficiently and robustly ...
    • Dealing with Childhood Obesity: Passive versus Active Activity Monitoring Approaches for Engaging Individuals in Exercise 

      Valentin, Giancarlo; Howard, Ayanna M. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-02)
      Childhood obesity is a growing health problem. Indicators show that the rate of obesity for children age 12-19 years old has risen from 5% percent to 18% over the last ten years. Strategies to solve this childhood obesity ...
    • Decentralized Adaptive Control of a Two Degree of Freedom Flexible Arm 

      Yuan, Bau-San; Book, Wayne John; Huggins, J. D. (Georgia Institute of TechnologyAmerican Society of Mechanical Engineers, 1989-12)
      A robust adaptive control is derived by signal-synthesis methods for a light, flexible two degree-of-freedom manipulator. The controller for each joint is decentralized, using measurements of one joint's position as ...
    • Decentralized Adaptive Control of Robot Manipulators with Robust Stabilization Design 

      Yuan, Bau-San; Book, Wayne John (Georgia Institute of TechnologyAmerican Control Conference, 1988-06)
      Due to geometric nonlinearities and complex dynamics, a decentralized technique for adaptive control for multilink robot arms is attractive. Lyapunov-function theory for stability analysis provides an approach to robust ...
    • Decentralized Classification in Societies of Autonomous and Heterogenous Robots 

      Martini, Simone; Fagiolini, Adriano; Zichittella, Giancarlo; Egerstedt, Magnus B.; Bicchi, Antonio (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2011-05)
      This paper addresses the classification problem for a set of autonomous robots that interact with each other. The objective is to classify agents that "behave" in "different way", due to their own physical dynamics or ...
    • Decentralized Degree Regularization for Multi-Agent Networks 

      Yazıcıoğlu, A. Yasin; Egerstedt, Magnus B.; Shamma, Jeff S. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-12)
      Networked multi-agent systems are widely modeled as graphs where the agents are represented as nodes and edges exist between the agents that interact directly. In this setting, the degree of a node is the number of edges ...
    • Decentralized Formation of Random Regular Graphs or Robust Multi-Agent Networks 

      Yazıcıoğlu, A. Yasin; Egerstedt, Magnus B.; Shamma, Jeff S. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-12)
      Multi-agent networks are often modeled via interaction graphs, where the nodes represent the agents and the edges denote direct interactions between the corresponding agents. Interaction graphs have significant impact on ...
    • Decentralized Formation Selection Mechanisms Inspired by Foraging Bottlenose Dolphins 

      Haque, Musad A.; Egerstedt, Magnus B. (Georgia Institute of Technology, 2008-07)
    • Decision Making in Robots and Animals 

      Lee, Daniel (2016-03-09)
      Current artificial intelligence systems for perception and action incorporate a number of techniques: optimal observer models, Bayesian filtering, probabilistic mapping, trajectory planning, dynamic navigation, and feedback ...
    • Decoding Children’s Social Behavior 

      Rehg, James M.; Abowd, Gregory D.; Rozga, Agata; Romero, Mario; Clements, Mark A.; Sclaroff, Stan; Essa, Irfan; Ousley, Opal Y.; Li, Yin; Kim, Chanho; Rao, Hrishikesh; Kim, Jonathan C.; Presti, Liliana Lo; Zhang, Jianming; Lantsman, Denis; Bidwell, Jonathan; Ye, Zhefan (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-06)
      We introduce a new problem domain for activity recognition: the analysis of children’s social and communicative behaviors based on video and audio data. We specifically target interactions between children aged 1–2 ...
    • Decoupling Behavior, Perception, and Control for Autonomous Learning of Affordances 

      Hermans, Tucker; Rehg, James M.; Bobick, Aaron F. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-05)
      A novel behavior representation is introduced that permits a robot to systematically explore the best methods by which to successfully execute an affordance-based behavior for a particular object. The approach decomposes ...
    • Deep Segments: Comparisons between Scenes and their Constituent Fragments using Deep Learning 

      Doshi, Jigar; Mason, Celeste; Wagner, Alan; Kira, Zsolt (Georgia Institute of Technology, 2014-09)
      We examine the problem of visual scene understanding and abstraction from first person video. This is an important problem and successful approaches would enable complex scene characterization tasks that go beyond ...
    • Deformable-Medium Affordances for Interacting with Multi-Robot Systems 

      Diana, Matteo; de la Croix, Jean-Pierre; Egerstedt, Magnus B. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2013-11)
      This paper addresses the issue of human-swarm interactions by proposing a new set of affordances that make a multi-robot system amenable to human control. In particular, we propose to use clay – a deformable medium – as ...
    • The Degree of Nonholonomy in Distributed Computations 

      Costello, Zak; Egerstedt, Magnus B. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-12)
      A network of locally interacting agents can be thought of as performing a distributed computation. But not all computations can be faithfully distributed. This paper discusses which global linear transformations can be ...