scholarly journals Sensuator: A Hybrid Sensor–Actuator Approach to Soft Robotic Proprioception Using Recurrent Neural Networks

Actuators ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 30
Author(s):  
Pornthep Preechayasomboon ◽  
Eric Rombokas
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Linear Models ◽  
Open Loop ◽  
Proof Of Concept ◽  
State Estimator ◽  
Loop Control ◽  
Practical Applications ◽  
Soft Actuator ◽  
The Cost

Soft robotic actuators are now being used in practical applications; however, they are often limited to open-loop control that relies on the inherent compliance of the actuator. Achieving human-like manipulation and grasping with soft robotic actuators requires at least some form of sensing, which often comes at the cost of complex fabrication and purposefully built sensor structures. In this paper, we utilize the actuating fluid itself as a sensing medium to achieve high-fidelity proprioception in a soft actuator. As our sensors are somewhat unstructured, their readings are difficult to interpret using linear models. We therefore present a proof of concept of a method for deriving the pose of the soft actuator using recurrent neural networks. We present the experimental setup and our learned state estimator to show that our method is viable for achieving proprioception and is also robust to common sensor failures.

scholarly journals Recovery of dynamics and function in spiking neural networks by closed-loop control

2015 ◽  
Author(s):  
Ioannis Vlachos ◽  
Taskin Deniz ◽  
Ad Aertsen ◽  
Arvind Kumar
Keyword(s):  
Neural Networks ◽  
Closed Loop ◽  
Brain Activity ◽  
Open Loop ◽  
Spiking Neural Networks ◽  
Delayed Feedback Control ◽  
Loop Control ◽  
Wide Range ◽  
Underlying Network ◽  
And Function

There is a growing interest in developing novel brain stimulation methods to control disease-related aberrant neural activity and to address basic neuroscience questions. Conventional methods for manipulating brain activity rely on open-loop approaches that usually lead to excessive stimulation and, crucially, do not restore the original computations performed by the network. Thus, they are often accompanied by undesired side-effects. Here, we introduce delayed feedback control (DFC), a conceptually simple but effective method, to control pathological oscillations in spiking neural networks. Using mathematical analysis and numerical simulations we show that DFC can restore a wide range of aberrant network dynamics either by suppressing or enhancing synchronous irregular activity. Importantly, DFC besides steering the system back to a healthy state, it also recovers the computations performed by the underlying network. Finally, using our theory we isolate the role of single neuron and synapse properties in determining the stability of the closed-loop system.

scholarly journals Recurrent Kernel Machines: Computing with Infinite Echo State Networks

2012 ◽  
Vol 24 (1) ◽  
pp. 104-133 ◽  
Author(s):  
Michiel Hermans ◽  
Benjamin Schrauwen
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Input Data ◽  
Dimensional Space ◽  
Theoretical Research ◽  
High Dimensional ◽  
Support Vector ◽  
Practical Applications ◽  
Echo State Networks ◽  
Vector Machines

Echo state networks (ESNs) are large, random recurrent neural networks with a single trained linear readout layer. Despite the untrained nature of the recurrent weights, they are capable of performing universal computations on temporal input data, which makes them interesting for both theoretical research and practical applications. The key to their success lies in the fact that the network computes a broad set of nonlinear, spatiotemporal mappings of the input data, on which linear regression or classification can easily be performed. One could consider the reservoir as a spatiotemporal kernel, in which the mapping to a high-dimensional space is computed explicitly. In this letter, we build on this idea and extend the concept of ESNs to infinite-sized recurrent neural networks, which can be considered recursive kernels that subsequently can be used to create recursive support vector machines. We present the theoretical framework, provide several practical examples of recursive kernels, and apply them to typical temporal tasks.

Prediction of Machine Deterioration Using Vibration Based Fault Trends and Recurrent Neural Networks

1999 ◽  
Vol 121 (3) ◽  
pp. 355-362 ◽  
Author(s):  
P. W. Tse ◽  
D. P. Atherton
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Production Cost ◽  
Market Competition ◽  
Spare Parts ◽  
Remaining Life ◽  
Substantial Portion ◽  
Market Shares ◽  
The Cost ◽  
Machine Deterioration

High market competition for sales requires companies to reduce the cost of production if they are to maintain their market shares. Since the cost of maintenance contributes a substantial portion of the production cost, companies must budget maintenance effectively. Machine deterioration prognosis can decrease the cost of maintenance by minimizing the loss of production due to machine breakdown and avoiding the overstocking of spare parts. A new prognostic method is described in this paper which has been developed to forecast the rate of machine deterioration using recurrent neural networks. From tests applying the method to the prediction of nonlinear sunspot activities and vibration based fault trends of several industrial machines, the results have shown that the method is promising. It not only evaluates the seriousness of damage caused by faults, but also forecasts the remaining life span of defective components.

The Design and Simulation of a High Force Low Power Actuation System for Camless Engines

2005 ◽  
Author(s):  
J. H. Lumkes ◽  
W. Van Doorn ◽  
J. Donaldson
Keyword(s):  
Power Efficiency ◽  
Open Loop ◽  
Operating Conditions ◽  
Loop Control ◽  
Actuation System ◽  
Camless Engines ◽  
In Series ◽  
The Cost ◽  
Parameter Values ◽  
Valve Actuation

Camless engines require independent actuators which can provide accurate control, sufficient force, and yet only require a small percentage of engine output power. A valve actuation system that meets these requirements is designed, modeled, and simulated at engine speeds up to 6000 rpm. Based on consideration of valve actuation cycles and hydraulic power efficiency, an open-center system employing control valves in series is simulated under various operating conditions and using a range of design parameter values. The results demonstrate that the proposed system is capable of meeting the 6000 rpm engine speed requirement while using as little as 1–2% of available engine power. In addition, the system lends itself well to either open-loop or closed-loop control without requiring a separate position sensor on each engine valve [1]. This potentially reduces the cost and increases the reliability of an actuation system designed for camless engines.

scholarly journals Study of the impact of the COVID-19 pandemic on international air transportation

2021 ◽  
Vol 29 (1) ◽  
pp. 22-35
Author(s):  
Eugeny Yu. Shchetinin
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Stock Prices ◽  
Short Term Memory ◽  
Air Transportation ◽  
Time Series Forecasting ◽  
The Cost ◽  
The Impact

Time Series Forecasting has always been a very important area of research in many domains because many different types of data are stored as time series. Given the growing availability of data and computing power in the recent years, Deep Learning has become a fundamental part of the new generation of Time Series Forecasting models, obtaining excellent results.As different time series problems are studied in many different fields, a large number of new architectures have been developed in recent years. This has also been simplified by the growing availability of open source frameworks, which make the development of new custom network components easier and faster.In this paper three different Deep Learning Architecture for Time Series Forecasting are presented: Recurrent Neural Networks (RNNs), that are the most classical and used architecture for Time Series Forecasting problems; Long Short-Term Memory (LSTM), that are an evolution of RNNs developed in order to overcome the vanishing gradient problem; Gated Recurrent Unit (GRU), that are another evolution of RNNs, similar to LSTM.The article is devoted to modeling and forecasting the cost of international air transportation in a pandemic using deep learning methods. The author builds time series models of the American Airlines (AAL) stock prices for a selected period using LSTM, GRU, RNN recurrent neural networks models and compare the accuracy forecast results.

scholarly journals Without Diagonal Nonlinear Requirements: The More GeneralP-Critical Dynamical Analysis for UPPAM Recurrent Neural Networks

2013 ◽  
Vol 2013 ◽  
pp. 1-10
Author(s):  
Xi Chen ◽  
Huizhong Mao ◽  
Chen Qiao
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Continuous Time ◽  
Dynamical Analysis ◽  
Critical Conditions ◽  
Boundary Line ◽  
Practical Applications ◽  
Asymptotical Stable ◽  
Stability Results ◽  
Activation Mapping

Continuous-time recurrent neural networks (RNNs) play an important part in practical applications. Recently, due to the ability of assuring the convergence of the equilibriums on the boundary line between stable and unstable, the study on the critical dynamics behaviors of RNNs has drawn especial attentions. In this paper, a new asymptotical stable theorem and two corollaries are presented for the unified RNNs, that is, the UPPAM RNNs. The analysis results given in this paper are under the generallyP-critical conditions, which improve substantially upon the existing relevant critical convergence and stability results, and most important, the compulsory requirement of diagonally nonlinear activation mapping in most recent researches is removed. As a result, the theory in this paper can be applied more generally.

Sign in / Sign up

Export Citation Format

Share Document