Artículos de Revista

Examinar

Examinando Artículos de Revista por Materia "1203.04 Inteligencia Artificial"

Seleccione resultados tecleando las primeras letras
Mostrando 1 - 3 de 3
  • Miniatura
    Ítem
    Path Routing Optimization for STM Ultrasound Rendering
    (Institute of Electrical and Electronics Engineers, 2020-02) Barreiro, Hector; Sinclair, Stephen; Otaduy, Miguel A.
    Ultrasound transducer arrays are capable of producing tactile sensations on the hand, promising hands-free haptic interaction for virtual environments. However, controlling such an array with respect to reproducing a desired perceived interaction remains a challenging problem. In this work we approach this problem as a dynamic mapping of virtual interactions to existing control metaphors of ultrasound devices, namely, the modulation of focal point positions and intensities over time, a method known as Spatiotemporal Modulation (STM). In particular, we propose an optimization approach that takes into account known perceptual parameters and limitations of the STM method. This results in a set of focal point paths optimized to best reconstruct an arbitrary target pressure field.
  • Miniatura
    Ítem
    Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera
    (ACM Transactions on Graphics, 2019) Mueller, Franziska; Davis, Micah; Bernard, Florian; Sotnychenko, Oleksandr; Verschoor, Mickeal; Otaduy, Miguel A.; Casas, Dan; Theobalt, Christian
    Wepresentanovelmethodforreal-timeposeandshapereconstructionof twostronglyinteractinghands.Ourapproachisthefirsttwo-handtracking solutionthatcombinesanextensivelistoffavorableproperties,namelyitis marker-less,usesasingleconsumer-leveldepthcamera,runsinrealtime, handlesinter-andintra-handcollisions,andautomaticallyadjuststothe user’shandshape.Inordertoachievethis,weembedarecentparametric handposeandshapemodelandadensecorrespondencepredictorbasedon adeepneuralnetworkintoasuitableenergyminimizationframework.For trainingthecorrespondencepredictionnetwork,wesynthesizeatwo-hand dataset based on physical simulations that includes both hand pose and shapeannotationswhileatthesametimeavoidinginter-handpenetrations. Toachievereal-timerates,wephrasethemodelfittingintermsofanonlinear least-squaresproblemsothattheenergycanbeoptimizedbasedonahighly efficient GPU-based Gauss-Newton optimizer. We show state-of-the-art resultsinscenesthatexceedthecomplexityleveldemonstratedbyprevious
  • Miniatura
    Ítem
    Rendering of Constraints with Underactuated Haptic Devices
    (Institute of Electrical and Electronics Engineers, 2020-03-20) Lobo, Daniel; Otaduy, Miguel A.
    Several previous works have studied the application of proxy-based rendering algorithms to underactuated haptic devices. However, all these works make oversimplifying assumptions about the configuration of the haptic device, and they ignore the user’s intent. In this work, we lift those assumptions, and we carry out a theoretical study that unveils the existence of unnatural ghost forces under typical proxy-based rendering. We characterize and quantify those ghost forces. In addition, we design a novel rendering strategy, with anisotropic coupling between the device and the proxy. With this strategy, the forces rendered by an underactuated device are a best match of the forces rendered by a fully actuated device. We have demonstrated our findings on synthetic experiments and a simple real-world experiment.