Search for: All records

Tactile sensing for robotics is achieved through a variety of mechanisms, including magnetic, optical-tactile, and conductive fluid. Currently, the fluid-based sensors have struck the right balance of anthropomorphic sizes and shapes and accuracy of tactile response measurement. However, this design is plagued by a low Signal to Noise Ratio (SNR) due to the fluid based sensing mechanism “damping” the measurement values that are hard to model. To this end, we present a spatio-temporal gradient representation on the data obtained from fluid-based tactile sensors, which is inspired from neuromorphic principles of event based sensing. We present a novel algorithm (GradTac) that converts discrete data points from spatial tactile sensors into spatio-temporal surfaces and tracks tactile contours across these surfaces. Processing the tactile data using the proposed spatio-temporal domain is robust, makes it less susceptible to the inherent noise from the fluid based sensors, and allows accurate tracking of regions of touch as compared to using the raw data. We successfully evaluate and demonstrate the efficacy of GradTac on many real-world experiments performed using the Shadow Dexterous Hand, equipped with the BioTac SP sensors. Specifically, we use it for tracking tactile input across the sensor’s surface, measuring relative forces, detecting linear andmore »rotational slip, and for edge tracking. We also release an accompanying task-agnostic dataset for the BioTac SP, which we hope will provide a resource to compare and quantify various novel approaches, and motivate further research.« less

Recent advancements in deep learning have led to drastic improvements in speech segregation models. Despite their success and growing applicability, few efforts have been made to analyze the underlying principles that these networks learn to perform segregation. Here we analyze the role of harmonicity on two state-of-the-art Deep Neural Networks (DNN)-based models- Conv-TasNet and DPT-Net [1],[2]. We evaluate their performance with mixtures of natural speech versus slightly manipulated inharmonic speech, where harmonics are slightly frequency jittered. We find that performance deteriorates significantly if one source is even slightly harmonically jittered, e.g., an imperceptible 3% harmonic jitter degrades performance of Conv-TasNet from 15.4 dB to 0.70 dB. Training the model on inharmonic speech does not remedy this sensitivity, instead resulting in worse performance on natural speech mixtures, making inharmonicity a powerful adversarial factor in DNN models. Furthermore, additional analyses reveal that DNN algorithms deviate markedly from biologically inspired algorithms [3] that rely primarily on timing cues and not harmonicity to segregate speech.

Neuromorphic vision sensors (NVS), also known as silicon retina, capture aspects of the biological functionality of the mammalian retina by transducing incident photocurrent into an asynchronous stream of spikes that denote positive and negative changes in intensity. Current state-of-the-art devices are effectively leveraged in a variety of settings, but still suffer from distinct disadvantages as they are transitioned into high performance environments, such as space and autonomy. This paper provides an outline and demonstration of a data synthesis tool that gleans characteristics from the retina and allows the user to not only convert traditional video into neuromorphic data, but characterize design tradeoffs and inform future endeavors. Our retinomorphic model, RetinoSim, incorporates aspects of current NVS to allow for accurate data conversion while providing biologically-inspired features to improve upon this baseline. RetinoSim was implemented in MATLAB with a Graphical User Interface frontend to allow for expeditious video conversion and architecture exploration. We demonstrate that the tool can be used for real-time conversion for sparse event streams, exploration of frontend configurations, and duplication of existing event datasets.

Hyperdimensional Computing affords simple, yet powerful operations to create long Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for learning, and are dynamic enough to be modified on the fly. In this paper, we explore the notion of using binary hypervectors to directly encode the final, classifying output signals of neural networks in order to fuse differing networks together at the symbolic level. This allows multiple neural networks to work together to solve a problem, with little additional overhead. Output signals just before classification are encoded as hypervectors and bundled together through consensus summation to train a classification hypervector. This process can be performed iteratively and even on single neural networks by instead making a consensus of multiple classification hypervectors. We find that this outperforms the state of the art, or is on a par with it, while using very little overhead, as hypervector operations are extremely fast and efficient in comparison to the neural networks. This consensus process can learn online and even grow or lose models in real-time. Hypervectors act as memories that can be stored, and even further bundled together over time, affording life long learning capabilities. Additionally, this consensus structure inherits the benefits ofmore »Hyperdimensional Computing, without sacrificing the performance of modern Machine Learning. This technique can be extrapolated to virtually any neural model, and requires little modification to employ - one simply requires recording the output signals of networks when presented with a testing example.« less

Current deep neural network approaches for camera pose estimation rely on scene structure for 3D motion estimation, but this decreases the robustness and thereby makes cross-dataset generalization difficult. In contrast, classical approaches to structure from motion estimate 3D motion utilizing optical flow and then compute depth. Their accuracy, however, depends strongly on the quality of the optical flow. To avoid this issue, direct methods have been proposed, which separate 3D motion from depth estimation, but compute 3D motion using only image gradients in the form of normal flow. In this paper, we introduce a network NFlowNet, for normal flow estimation which is used to enforce robust and direct constraints. In particular, normal flow is used to estimate relative camera pose based on the cheirality (depth positivity) constraint. We achieve this by formulating the optimization problem as a differentiable cheirality layer, which allows for end-to-end learning of camera pose. We perform extensive qualitative and quantitative evaluation of the proposed DiffPoseNet’s sensitivity to noise and its generalization across datasets. We compare our approach to existing state-of-the-art methods on KITTI, TartanAir, and TUM-RGBD datasets.

Little is known about how neural representations of natural sounds differ across species. For example, speech and music play a unique role in human hearing, yet it is unclear how auditory representations of speech and music differ between humans and other animals. Using functional ultrasound imaging, we measured responses in ferrets to a set of natural and spectrotemporally matched synthetic sounds previously tested in humans. Ferrets showed similar lower-level frequency and modulation tuning to that observed in humans. But while humans showed substantially larger responses to natural vs. synthetic speech and music in non-primary regions, ferret responses to natural and synthetic sounds were closely matched throughout primary and non-primary auditory cortex, even when tested with ferret vocalizations. This finding reveals that auditory representations in humans and ferrets diverge sharply at late stages of cortical processing, potentially driven by higher-order processing demands in speech and music.