arXiv research

Developed Taylor series for muscle-finger system analysis.

The paper presents a method to reduce arm motion complexity for prosthetics and robotics.

Graph Convolutional Networks improve prosthetic sensation interpretation.

Dual-stage sEMG classification improves gesture recognition accuracy.

Simple attention model outperforms complex sEMG classifiers.

A new learning method for prosthetic arms without explicit rewards.

In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants were invited to describe their algorithms. In this work, we describe the challenge and pre…

Non-invasive myoelectric prostheses require a long training time to obtain satisfactory control dexterity. These training times could possibly be reduced by leveraging over training efforts by previous subjects. So-called domain adaptation algorithms formalize this strategy and have indeed been shown to significantly r…

New sEMG dataset for ADL activities recognized with high accuracy.

Despite the recent progress in deep reinforcement learning field (RL), and, arguably because of it, a large body of work remains to be done in reproducing and carefully comparing different RL algorithms. We present catalyst.RL, an open source framework for RL research with a focus on reproducibility and flexibility. Ma…

Generative model improves EMG pattern recognition accuracy.

Co-adaptation is a special form of on-line learning where an algorithm $\mathcal{A}$ must assist an unknown algorithm $\mathcal{B}$ to perform some task. This is a general framework and has applications in recommendation systems, search, education, and much more. Today, the most common use of co-adaptive algorithms is …

Brain-computer interfaces (BCIs) have enabled prosthetic device control by decoding motor movements from neural activities. Neural signals recorded from cortex exhibit nonstationary property due to abrupt noises and neuroplastic changes in brain activities during motor control. Current state-of-the-art neural signal de…

New technologies for recording the activity of large neural populations during complex behavior provide exciting opportunities for investigating the neural computations that underlie perception, cognition, and decision-making. Nonlinear state space models provide an interpretable signal processing framework by combinin…

The true online TD(λ) algorithm has recently been proposed (van Seijen and Sutton, 2014) as a universal replacement for the popular TD(λ) algorithm, in temporal-difference learning and reinforcement learning. True online TD(λ) has better theoretical properties than conventional TD(λ), and the expectation is that it als…

FineHand learns hand shapes for better ASL recognition.

Traditional vision-based hand gesture recognition systems is limited under dark circumstances. In this paper, we build a hand gesture recognition system based on microwave transceiver and deep learning algorithm. A Doppler radar sensor with dual receiving channels at 5.8GHz is used to acquire a big database of hand ges…

DIGIT is a low-cost tactile sensor for in-hand manipulation.

One of the open challenges in designing robots that operate successfully in the unpredictable human environment is how to make them able to predict what actions they can perform on objects, and what their effects will be, i.e., the ability to perceive object affordances. Since modeling all the possible world interactio…

The classical trefoil is famous for having a three-colouring which distinguishes it from the unknot. The three-colouring is also notorious for not distinguishing the right handed from the left handed trefoil. However with a bit of tweaking the three colours can also be used for this task. What lies behind the method is…

Deep neural network improves hand gesture classification from wearable IMUs.

Transfer learning improves dynamic model transfer for soft robotic hands.

We prove that on compact Kähler manifolds solutions to the complex Monge-Ampère equation, with the the right hand side in $L^p, p>1,$ are Hölder continuous.

We review some cohomological aspects of complex and hypercomplex manifolds and underline the differences between both realms. Furthermore, we try to highlight the similarities between compact complex surfaces on one hand and compact hypercomplex manifolds of real dimension 8 with holonomy of the Obata connection in SL(…

Paper explores using hand gestures to type English letters.

In this paper, we extend the formal definition of topological surgery by introducing new notions in order to model natural phenomena exhibiting it. On the one hand, the common features of the presented natural processes are captured by our schematic models and, on the other hand, our new definitions provide the theoret…

Deep neural networks improve sEMG-based hand gesture classification.

We provide an interpretation of the APS index theorem of Piazza-Schick and Zeidler in terms of coarse homotopy theory. On the one hand we propose a motivic version of the boundary value problem, the index theorem, and the associated secondary invariants. On the other hand, we discuss in detail how the abstract version …

We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we randomize many of the physical properties of the system like friction coefficients…

We provide a benchmark dataset for hand gesture recognition using force myography.

We present a somewhat new proof to the $C^{2,α}$-aprori estimate for the uniform elliptic Monge-Ampere equations, in both the real and complex settings. Our estimates do not need to differentiate the equation, and only depends on the $C^{α^{\prime}}-$norm of the right hand side of the equation, $0<α<α^{\prime}$.

We consider spaces for which there is a notion of harmonicity for complex valued functions defined on them. For instance, this is the case of Riemannian manifolds on one hand, and (metric) graphs on the other hand. We observe that it is then possible to define an "amazing" notion of holomorphic functions on them, and s…

We consider the complex Monge-Ampére equation on complete Kähler manifolds with cusp singularity along a divisor when the right hand side $F$ has rather weak regularity. We proved that when the right hand side $F$ is in some \emph{weighted} $W^{1,p_0}$ space for $p_0 > 2n$, the Monge-Ampére equation has a classical $W^…

Note on gradient estimates for complex Monge-Ampere equation.

In this note we discuss the mathematical tools to define trend indicators which are used to describe market trends. We explain the relation between averages and moving averages on the one hand and the so called exponential moving average (EMA) on the other hand. We present a lot of examples and give the definition of t…

We prove that the geodesic flow on the unit tangent bundle to a hyperbolic 2-orbifold is left-handed if and only if the orbifold is a sphere with three conic points. As a consequence, on the unit tangent bundle to a 3-conic sphere, the lift of every finite collection of closed geodesics that is zero in integral homolog…

We investigate the relation between quadrics and their Christoffel duals on the one hand, and certain zero mean curvature surfaces and their Gauss maps on the other hand. To study the relation between timelike minimal surfaces and the Christoffel duals of 1-sheeted hyperboloids we introduce para-holomorphic elliptic fu…

The substantial turmoil created by both 2000 dot-com crash and 2008 subprime crisis has fueled the belief that the two classical paradigms of economics, which are the invisible hand and the rational agent, are not appropriate to describe market dynamics and should be abandoned at the benefit of alternative new theoreti…

Study shows patterns in Stein fillability of trefoil surgeries.

This technical note extends recent results on the computational complexity of globally minimizing the error of piecewise-affine models to the related problem of minimizing the error of switching linear regression models. In particular, we show that, on the one hand the problem is NP-hard, but on the other hand, it admi…

Classifies 4D toric Hermitian ALF metrics with conical singularities.

We build CSI-Net, a unified Deep Neural Network~(DNN), to learn the representation of WiFi signals. Using CSI-Net, we jointly solved two body characterization problems: biometrics estimation (including body fat, muscle, water, and bone rates) and person recognition. We also demonstrated the application of CSI-Net on tw…

In this paper we construct a properly embedded holomorphic disc in the unit ball $\mathbb{B}^2$ of $\mathbb{C}^2$ having a surprising combination of properties: on the one hand, it has finite area and hence is the zero set of a bounded holomorphic function on $\mathbb{B}^2$; on the other hand, its boundary curve is eve…

Existence and uniqueness of bounded solutions to complex Monge-Ampère flows on Kähler manifolds.

Highly connected orbifolds are rare but exist.

This paper studies gradient almost Ricci-harmonic soliton with respect to a fixed metric. We rely on analytic techniques to estabilish some basic elliptic and integral equations for the structure of almost Ricci-harmonic soliton which generalizes that of Ricci-hamonic solitons on one hand and that of almost Ricci solit…

We extend the notion of what it means for a complete Ricci flow to have a given initial metric, and consider the resulting well-posedness issues that arise in the 2D case. On one hand we construct examples of nonuniqueness by showing that surfaces with cusps can evolve either by keeping the cusps or by contracting them…

Let Πbe a link projection in S^2. John Conway and later Francis Bonahon and Larry Siebenmann undertook to split $Π$ into canonical pieces. These pieces received different names: basic or polyhedral diagrams on one hand, rational, algebraic, bretzel, arborescent diagrams on the other hand. This paper proposes a thorough…