Liquid State Machine to Generate the Movement Profiles for the Gait Cycle of a 6 DOF Bipedal Robot in a Sagittal Plane

2018 ◽  
Author(s):  
Jesús Franco-Robles ◽  
Alejandro De Lucio-Rangel ◽  
Karla A. Camarillo-Gómez ◽  
Gerardo I. Pérez-Soto ◽  
Jesús Rivera-Guillén
Keyword(s):  
Time Series ◽  
Multilayer Perceptron ◽  
Liquid State ◽  
Gait Cycle ◽  
Sagittal Plane ◽  
Experimental Result ◽  
Forward Kinematics ◽  
Neuronal System ◽  
Bipedal Robot ◽  
Input Time

In this paper, a neuronal system with the ability to generate motion profiles and profiles of the ZMP in a 6DoF bipedal robot in the sagittal plane, is presented. The input time series for LSM training are movement profiles of the oscillating foot trajectory obtained by forward kinematics performed by a previously trained ANN multilayer perceptron. The profiles of objective movement for training are acquired from the analysis of the human walk. Based on a previous simulation of the bipedal robot, a profile of the objective ZMP will be generated for the y–axis and another for the z–axis to know its behavior during the training walk. As an experimental result, the LSM generates new motion profiles and ZMP, given a different trajectory with which it was trained. With the LSM it will be possible to propose new trajectories of the oscillating foot, where it will be known if this trajectory will be stable, by the ZMP, and what movement profile for each articulation will be required to reach this trajectory.

Liquid State Machine to Generate the Movement Profiles for the Gait Cycle of a Six Degrees-of-Freedom Bipedal Robot in a Sagittal Plane

2019 ◽  
Vol 142 (1) ◽  
Author(s):  
Jesús Franco-Robles ◽  
Alejandro De Lucio-Rangel ◽  
Karla A. Camarillo-Gómez ◽  
Gerardo I. Pérez-Soto ◽  
Miguel A. Martínez-Prado
Keyword(s):  
Time Series ◽  
Liquid State ◽  
Degrees Of Freedom ◽  
Gait Cycle ◽  
Sagittal Plane ◽  
State Machine ◽  
Supervised Machine Learning ◽  
Human Gait ◽  
Bipedal Robot ◽  
Six Degrees Of Freedom

Abstract In this paper, an approach based on a liquid state machine (LSM) to compute the movement profiles to achieve a gait pattern subject to different variations in its trajectory is presented. At the same time, the position of the zero moment point (ZMP) to determine the stability of the six degrees-of-freedom (6DOF) bipedal robot in the sagittal plane during the gait cycle is calculated. The system is constructed as a supervised machine learning model. The time series of the oscillating foot trajectory obtained by direct kinematics with a multilayer perceptron neural network (MLP), to strengthen the kinematic model, is considered as input values for training. The target movement profiles are acquired of a human gait cycle analysis in three different scenarios: normal gait, climbing stairs, and descending stairs. In training, this model also gets the trajectories of the ZMP position during the gait cycle, as target time series. The LSM formed by spiking neurons, considered as third-generation neural networks, is compared in the accuracy of prediction, by the dynamic time warping (DTW) technique and correlation analysis, against the human gait analysis database. With this neuronal system, the joint positions to generate a trajectory of the oscillating foot and the ZMP position of the bipedal in the sagittal plane in different scenarios are obtained, proving the robustness of the LSM.

Symmetry function as a new tool for evaluating the symmetry of gait in transfemoral amputees

2020 ◽  
Author(s):  
Slawomir Winiarski ◽  
Alicja Rutkowska-Kucharska ◽  
Mateusz Kowal
Keyword(s):  
Time Series ◽  
Gait Cycle ◽  
Sagittal Plane ◽  
Reaction Force ◽  
Frontal Plane ◽  
Symmetry Function ◽  
The Difference ◽  
Force Components ◽  
Analysis System ◽  
And Shifts

Abstract Background: Numerous studies have demonstrated significant asymmetries in unilateral amputee gait. The underlying dissimilarities between prosthetic and intact limbs have not yet been widely examined. To gain more insight into the functionality of asymmetries, we propose a new tool, the symmetry function (SF), to evaluate the symmetry of walking in terms of kinematic and dynamic variables of patients after unilateral transfemoral amputation and to identify areas with the largest side deviations in the movement cycle. Methods: An instrumented motion analysis system was used to register the gait of fourteen patients after unilateral trans-femoral amputation (TFA). Measurements involved evaluating the time series of gait variables characterizing a range of motion and the time series of the ground reaction force components. Comparison of the involved limb with the uninvolved limb in TFA patients was carried out on the basis of the SF values.Results: The symmetry function proved to be an excellent tool to localize the regions of asymmetry and their positive or negative directions in the full gait cycle. The difference between sides revealed by the symmetry function was the highest for the pelvis and the hip. In the sagittal plane, the pelvis was asymmetrically tilted, reaching the highest SF value of more than 25% at 60% cycle time. In the transverse plane, the pelvis was even more asymmetrically positioned throughout the entire gait cycle (50% difference on average). The hip in the frontal plane reached a 60% difference in SF throughout the single support phase for the prosthetic and then for the intact limb. Conclusions: The symmetry function allows for the detection of gait asymmetries and shifts in the center of gravity and may assess the precise in time adaptation of prostheses and rehabilitation monitoring, especially in unilateral impairments.Trial registration: The trial registration number (TRN): 379991 issued by the Australian New Zealand Clinical Trials Registry (ANZCTR) on 07.05.2020 (retrospectively registered).

IDENTIFYING DISTINCT STOCHASTIC DYNAMICS FROM CHAOS: A STUDY ON MULTIMODAL NEURAL FIRING PATTERNS

2009 ◽  
Vol 19 (02) ◽  
pp. 453-485 ◽  
Author(s):  
MINGHAO YANG ◽  
ZHIQIANG LIU ◽  
LI LI ◽  
YULIN XU ◽  
HONGJV LIU ◽  
...  
Keyword(s):  
Time Series ◽  
Limit Cycle ◽  
Stochastic Dynamics ◽  
Nonlinear Time Series ◽  
Special Importance ◽  
Neuronal System ◽  
Neural Firing ◽  
Firing Patterns ◽  
Theoretical Simulation ◽  
Definition Of

Some chaotic and a series of stochastic neural firings are multimodal. Stochastic multimodal firing patterns are of special importance because they indicate a possible utility of noise. A number of previous studies confused the dynamics of chaotic and stochastic multimodal firing patterns. The confusion resulted partly from inappropriate interpretations of estimations of nonlinear time series measures. With deliberately chosen examples the present paper introduces strategies and methods of identification of stochastic firing patterns from chaotic ones. Aided by theoretical simulation we show that the stochastic multimodal firing patterns result from the effects of noise on neuronal systems near to a bifurcation between two simpler attractors, such as a point attractor and a limit cycle attractor or two limit cycle attractors. In contrast, the multimodal chaotic firing trains are generated by the dynamics of a specific strange attractor. Three systems were carefully chosen to elucidate these two mechanisms. An experimental neural pacemaker model and the Chay mathematical model were used to show the stochastic dynamics, while the deterministic Wang model was used to show the deterministic dynamics. The usage and interpretation of nonlinear time series measures were systematically tested by applying them to firing trains generated by the three systems. We successfully identified the distinct differences between stochastic and chaotic multimodal firing patterns and showed the dynamics underlying two categories of stochastic firing patterns. The first category results from the effects of noise on the neuronal system near a Hopf bifurcation. The second category results from the effects of noise on the period-adding bifurcation between two limit cycles. Although direct application of nonlinear measures to interspike interval series of these firing trains misleadingly implies chaotic properties, definition of eigen events based on more appropriate judgments of the underlying dynamics leads to accurate identifications of the stochastic properties.

Functional Data Analyses for the Assessment of Joint Power Profiles During Gait of Stroke Subjects

2014 ◽  
Vol 30 (2) ◽  
pp. 348-352 ◽  
Author(s):  
André G. P. Andrade ◽  
Janaine C. Polese ◽  
Leopoldo A. Paolucci ◽  
Hans-Joachim K. Menzel ◽  
Luci F. Teixeira-Salmela
Keyword(s):  
Power Generation ◽  
Gait Cycle ◽  
Sagittal Plane ◽  
Plantar Flexion ◽  
Knee Extension ◽  
Mathematical Function ◽  
Joint Power ◽  
Gait Biomechanics ◽  
Isolated Points ◽  
Parametric Analyses

Lower extremity kinetic data during walking of 12 people with chronic poststroke were reanalyzed, using functional analysis of variance (FANOVA). To perform the FANOVA, the whole curve is represented by a mathematical function, which spans the whole gait cycle and avoids the need to identify isolated points, as required for traditional parametric analyses of variance (ANOVA). The power variables at the ankle, knee, and hip joints, in the sagittal plane, were compared between two conditions: With and without walking sticks at comfortable and fast speeds. For the ankle joint, FANOVA demonstrated increases in plantar flexion power generation during 60–80% of the gait cycle between fast and comfortable speeds with the use of walking sticks. For the knee joint, the use of walking sticks resulted in increases in the knee extension power generation during 10–30% of the gait cycle. During both speeds, the use of walking sticks resulted in increased power generation by the hip extensors and flexors during 10–30% and 40–70% of the gait cycle, respectively. These findings demonstrated the benefits of applying the FANOVA approach to improve the knowledge regarding the effects of walking sticks on gait biomechanics and encourage its use within other clinical contexts.

scholarly journals Design and Voluntary Motion Intention Estimation of a Novel Wearable Full-Body Flexible Exoskeleton Robot

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Chunjie Chen ◽  
Xinyu Wu ◽  
Du-xin Liu ◽  
Wei Feng ◽  
Can Wang
Keyword(s):  
Gait Cycle ◽  
Human Motion ◽  
Experimental Result ◽  
Motion Patterns ◽  
Exoskeleton Robot ◽  
Gait Phase ◽  
Phase Recognition ◽  
Motion Intention ◽  
Full Body ◽  
Testing Set

The wearable full-body exoskeleton robot developed in this study is one application of mobile cyberphysical system (CPS), which is a complex mobile system integrating mechanics, electronics, computer science, and artificial intelligence. Steel wire was used as the flexible transmission medium and a group of special wire-locking structures was designed. Additionally, we designed passive joints for partial joints of the exoskeleton. Finally, we proposed a novel gait phase recognition method for full-body exoskeletons using only joint angular sensors, plantar pressure sensors, and inclination sensors. The method consists of four procedures. Firstly, we classified the three types of main motion patterns: normal walking on the ground, stair-climbing and stair-descending, and sit-to-stand movement. Secondly, we segregated the experimental data into one gait cycle. Thirdly, we divided one gait cycle into eight gait phases. Finally, we built a gait phase recognition model based on k-Nearest Neighbor perception and trained it with the phase-labeled gait data. The experimental result shows that the model has a 98.52% average correct rate of classification of the main motion patterns on the testing set and a 95.32% average correct rate of phase recognition on the testing set. So the exoskeleton robot can achieve human motion intention in real time and coordinate its movement with the wearer.

scholarly journals Detecting dynamical anomalies in time series from different palaeoclimate proxy archives using windowed recurrence network analysis

2019 ◽  
Author(s):  
Jaqueline Lekscha ◽  
Reik V. Donner
Keyword(s):  
Time Series ◽  
Network Analysis ◽  
Nonlinear Filtering ◽  
Ice Cores ◽  
Second Step ◽  
Different Types ◽  
Output Time ◽  
Input Time ◽  
Past Climate Variability ◽  
Input Time Series

Abstract. Analysing palaeoclimate proxy time series using windowed recurrence network analysis (wRNA) has been shown to provide valuable information on past climate variability. In turn, it has also been found that the robustness of the obtained results differs among proxies from different palaeoclimate archives. To systematically test the suitability of wRNA for studying different types of palaeoclimate proxy time series, we use the framework of forward proxy modelling. For this, we create artificial input time series with different properties and, in a first step, compare the time series properties of the input and the model output time series. In a second step, we compare the areawise significant anomalies detected using wRNA. For proxies from tree and lake archives, we find that significant anomalies present in the input time series are sometimes missed in the input time series after the nonlinear filtering by the corresponding models. For proxies from speleothems, we observe falsely identified significant anomalies that are not present in the input time series. Finally, for proxies from ice cores, the wRNA results show the best correspondence with those for the input data. Our results contribute to improve the interpretation of windowed recurrence network analysis results obtained from real-world palaeoclimate time series.

scholarly journals Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks

2021 ◽  
Author(s):  
Kei Ishida ◽  
Masato Kiyama ◽  
Ali Ercan ◽  
Motoki Amagasaki ◽  
Tongbi Tu
Keyword(s):  
Time Series ◽  
Time Scale ◽  
Time Series Data ◽  
Series Data ◽  
Computational Time ◽  
Rainfall Runoff ◽  
Runoff Modeling ◽  
Input Time ◽  
Target Data ◽  
Resolution Data

Abstract This study proposes two effective approaches to reduce the required computational time of the training process for time-series modeling through a recurrent neural network (RNN) using multi-time-scale time-series data as input. One approach provides coarse and fine temporal resolutions of the input time-series data to RNN in parallel. The other concatenates the coarse and fine temporal resolutions of the input time-series data over time before considering them as the input to RNN. In both approaches, first, the finer temporal resolution data are utilized to learn the fine temporal scale behavior of the target data. Then, coarser temporal resolution data are expected to capture long-duration dependencies between the input and target variables. The proposed approaches were implemented for hourly rainfall–runoff modeling at a snow-dominated watershed by employing a long short-term memory network, which is a type of RNN. Subsequently, the daily and hourly meteorological data were utilized as the input, and hourly flow discharge was considered as the target data. The results confirm that both of the proposed approaches can reduce the required computational time for the training of RNN significantly. Lastly, one of the proposed approaches improves the estimation accuracy considerably in addition to computational efficiency.

Assessing Nitrogen Legacies in Western Europe

2021 ◽  
Author(s):  
Andreas Musolff ◽  
Sophie Ehrhardt ◽  
Rémi Dupas ◽  
Rohini Kumar ◽  
Pia Ebeling ◽  
...  
Keyword(s):  
Time Series ◽  
Agricultural Land ◽  
Time Lags ◽  
Water Safety ◽  
Biological Fixation ◽  
Nitrogen Inputs ◽  
Wide Range ◽  
N Input ◽  
Nitrate Concentrations ◽  
Input Time

<p>Intensive agricultural land use have introduced vast quantities of nutrients such as reactive nitrogen (N) to soils and subsequently to groundwater and surface waters. High nitrate concentrations are still a pressing issue for drinking water safety and aquatic ecosystem health e.g. in Europe, although fertilizer inputs have been significantly lowered in the last decades. This is partly due to a slow response of riverine nitrate concentrations to changes in nitrogen inputs attributed to N legacies in catchments. N can be stored organically bound as a biogeochemical legacy in soils or can be slowly transported as nitrate in groundwater forming a hydrologic legacy. Legacy can thus lead to a net retention of N in catchments and to substantial time lags in the response to input changes. Here, we systematically explore legacy effects over a wide range of catchment in the Western European countries France and Germany. We are making use of long observational time series of nitrate concentration in 238 catchments covering 40% of the total area of France and Germany. We apply a Weighted Regression on Time, Discharge, and Season (WRTDS) to derive continuous daily flow-normalized concentrations and loads. The temporal pattern of concentration and loads at the catchment outlet is compared to the N input time series evolving from agricultural N surplus, atmospheric deposition and biological fixation. We found that on long-term catchments retain on average 72% of the N input. Time lags between input and output were successfully explained by a lognormal transport time distribution. The modes of these distributions were found to be rather short with a median mode of 5.4 years across all catchments. Based on this data-driven assessment only the fate of N in the catchments is hard to assess as denitrification in soil and groundwater can lead to similar observations as the storage of N in legacies. Focusing on the mobile part of N that is exported by catchments, we estimate that a substantial amount of N is still stored in the subsurface that will be released in the coming years. We therefore analyzed how catchment nitrate export will evolve under the scenario of a total cut down, reduced or constant future N inputs. We report the expected timescale of reaction to implemented measures to help tackling this pressing water quality problem.</p>

scholarly journals Normal human locomotion

1979 ◽  
Vol 3 (1) ◽  
pp. 4-12 ◽  
Author(s):  
J. Hughes ◽  
N. Jacobs
Keyword(s):  
Gait Cycle ◽  
Sagittal Plane ◽  
Human Locomotion ◽  
Actual Situation ◽  
General Statement ◽  
Basic Principles ◽  
Significant Events ◽  
Normal Human ◽  
Pathological Gait ◽  
Muscle Actions

A study of normal locomotion requires an understanding of both the movements and the force actions involved. This is equally true in appreciating the problems of pathological gait. The gait cycle is described in terms of the significant events which occur during both the stance and swing phases. The basic principles underlying the analysis of force actions in walking are briefly described. A simple example of force actions in the elbow joint is considered and the analysis extrapolated to provide a general statement regarding locomotion. This relates to the muscle actions required to resist turning actions at joints due to the force effects in walking and the corresponding forces in the joints themselves. The conventional display of information relating to joint actions is considered and compared with the actual situation. “Stick diagrams” of motion in the sagittal plane are used to identify and discuss the actions at the joints of the leg in walking. Comparisons are made between this and pathological gait—in particular that of the above-knee amputee.

Sign in / Sign up

Export Citation Format

Share Document