Search

This paper proposes a Gaussian process-based method for trajectory learning and generation of individualized gait motions at arbitrary user-designated walking speeds, intended to be used in generating reference motions for robotic gait rehabilitation systems. We utilize a nonlinear dimension reduction technique based on Gaussian process dynamical models (GPDMs), in which the internal dynamics is modeled as a second-order Markov process evolving in a lower-dimensional latent space. After the GPDM parameters are identified with training data obtained from gait motions of healthy subjects walking at different speeds, our method then employs Gaussian process regression (GPR) to predict the initial two states of the latent space dynamics from any arbitrary desired walking speed and the anthropometric parameters of the test subject. Motions are then generated by directly mapping the latent space dynamics to joint trajectories. Experimental studies involving more than 100 subjects indicate that our method generates gait patterns with 30% less mean square prediction errors compared to recent state-of-the-art methods, while also allowing for arbitrary user-specified walking speeds. [ABSTRACT FROM AUTHOR]

This paper presents design and implementation of a color wavefront holographic printer. The printer output is a white light viewable volume hologram composed as a two-dimensional (2-D) array of elemental holograms. The three-dimensional (3-D) input data for the printer are encoded as computer generated holograms (CGHs) displayed in succession on an amplitude type spatial light modulator. The printer optical head extracts and demagnifies the beam with the 3-D object information from the beam diffracted by the modulator to produce a small size elemental hologram. This allows for mosaic delivery of exposures at primary colors with each elemental hologram acting as a single color channel. Computer generation of digital contents is accelerated by design of a phase-added stereogram approach based on partitioning of each CGH. Bright 3-D reconstruction with a motion parallax at saturated colors from holograms of test objects is presented. The holograms are printed on a silver-halide emulsion. The achieved high quality proves feasibility of recording analog color volume holograms from digital contents by mosaic delivery of the primary colors. Two quality enhancement approaches are proposed and tested. [ABSTRACT FROM PUBLISHER]