UMD Theses and Dissertations

Permanent URI for this collectionhttp://hdl.handle.net/1903/3

New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a given thesis/dissertation in DRUM.

More information is available at Theses and Dissertations at University of Maryland Libraries.

Browse

Filters

2012 - 20172

Settings

Subject: search.filters.subject.Bio-Inspired

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    NEURO-INSPIRED AUGMENTATIONS OF UNSUPERVISED DEEP NEURAL NETWORKS FOR LOW-SWAP EMBODIED ROBOTIC PERCEPTION
    (2017) Shamwell, Earl Jared; Perlis, Donald; Neuroscience and Cognitive Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Despite the 3-4 saccades the human eye undergoes per second, humans perceive a stable, visually constant world. During a saccade, the projection of the visual world shifts on the retina and the net displacement on the retina would be identical if the entire visual world were instead shifted. However, humans are able to perceptually distinguish between these two conditions and perceive a stable world in the first condition, and amoving world in the second. Through new analysis, I show how biological mechanisms theorized to enable visual positional constancy implicitly contain rich, egocentric sensorimotor representations and with appropriate modeling and abstraction, artificial surrogates for these mechanisms can enhance the performance of robotic systems. In support of this view, I have developed a new class of neuro-inspired, unsupervised, heterogeneous, deep predictive neural networks that are approximately 5,000%-22,000% faster (depending on the network configuration) than state-of-the-art (SOA)dense approaches and with comparable performance. Each model in this new family of network architectures, dubbed LightEfference (LE) (Chapter 2), DeepEfference (DE) (Chapter 2), Multi-Hypothesis DeepEfference (MHDE) (Chapter 3), and Inertial DeepEfference (IDE) (Chapter 4) respectively, achieves its substantial runtime performance increase by leveraging the embodied nature of mobile robotics and performing early fusion of freely available heterogeneous sensor and motor/intentional information. With these architectures, I show how embedding extra-visual information meant to encode an estimate of an embodied agent’s immediate intention supports efficient computations of visual constancy and odometry and greatly increases computational efficiency compared to comparable single-modality SOA approaches.
  • Thumbnail Image
    Item
    Development of a Bio-Inspired Magnetostrictive Flow and Tactile Sensor
    (2012) Marana, Michael Adam; Flatau, Alison; Aerospace Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    A magnetostrictive sensor was designed, constructed, and evaluated for use as flow or tactile sensor. Vibrissa-like beams (whiskers) were cut from sheets of the magnetostrictive iron-gallium alloy, Galfenol. These beams were cantilevered, with the fixed end of the whisker attached to a permanent magnet to provide the whisker with a magnetic bias. The free portion of the whisker was quasi-statically loaded, causing the whisker-like sensor to bend. The bending-induced strain caused the magnetization of the whisker to change, resulting in a changing magnetic field in the area surrounding the whisker. The change in magnetic field was detected by a giant magnetoresistance (GMR) sensor placed in proximity to the whisker. Therefore, the electrical resistance change of the GMR sensor was a function of the bending in the whisker due to external forces. Prototype design was aided using a bidirectionally coupled magnetoelastic model for computer simulation. The prototype was tested and evaluated under tactile loading and low speed flow conditions.