The Experts below are selected from a list of 59667 Experts worldwide ranked by ideXlab platform
Levi J. Hargrove - One of the best experts on this subject based on the ideXlab platform.
-
Online adaptive neural control of a robotic lower limb prosthesis.
Journal of neural engineering, 2018Co-Authors: John A. Spanias, Ann M. Simon, Suzanne B. Finucane, Eric J. Perreault, Levi J. HargroveAbstract:Objective The purpose of this study was to develop and evaluate an adaptive intent recognition algorithm that continuously learns to incorporate a lower limb amputee's neural information (acquired via electromyography (EMG)) as they ambulate with a robotic leg prosthesis. Approach We present a powered lower limb prosthesis that was configured to acquire the user's neural information and kinetic/kinematic information from embedded Mechanical Sensors, and identify and respond to the user's intent. We conducted an experiment with eight transfemoral amputees over multiple days. EMG and Mechanical Sensor data were collected while subjects using a powered knee/ankle prosthesis completed various ambulation activities such as walking on level ground, stairs, and ramps. Our adaptive intent recognition algorithm automatically transitioned the prosthesis into the different locomotion modes and continuously updated the user's model of neural data during ambulation. Main results Our proposed algorithm accurately and consistently identified the user's intent over multiple days, despite changing neural signals. The algorithm incorporated 96.31% [0.91%] (mean, [standard error]) of neural information across multiple experimental sessions, and outperformed non-adaptive versions of our algorithm-with a 6.66% [3.16%] relative decrease in error rate. Significance This study demonstrates that our adaptive intent recognition algorithm enables incorporation of neural information over long periods of use, allowing assistive robotic devices to accurately respond to the user's intent with low error rates.
-
Effect of additional Mechanical Sensor data on an EMG-based pattern recognition system for a powered leg prosthesis
2015 7th International IEEE EMBS Conference on Neural Engineering (NER), 2015Co-Authors: John A. Spanias, Ann M. Simon, Kimberly A. Ingraham, Levi J. HargroveAbstract:Powered lower limb prostheses can improve amputees' ability to traverse stairs and ramps by providing positive Mechanical work at the knee and ankle joint. EMG signals have been proposed as one way of providing seamless mode transitions by using them in combination with embedded Mechanical Sensors as inputs to a pattern recognition system that predicts the user's desired locomotion mode. In this study, we have expanded the amount of Mechanical Sensor information to include data from an additional five degrees of freedom in the load cell, as well as calculated thigh and shank angles. The purpose of this study was to determine the impact of this additional information on the performance of an EMG-based pattern recognition system designed to predict the desired locomotion mode. Our results indicate that including the additional Mechanical Sensor signals decreased the error rates of the system for both steady-state and transitional steps when compared to the reduced Sensor set. We also found that EMG still decreased the error rate of the system, but to a lesser extent when using the additional Mechanical Sensors.
-
analysis of using emg and Mechanical Sensors to enhance intent recognition in powered lower limb prostheses
Journal of Neural Engineering, 2014Co-Authors: Aaron Young, Levi J. Hargrove, Todd A KuikenAbstract:Objective. The purpose of this study was to determine the contribution of electromyography (EMG) data, in combination with a diverse array of Mechanical Sensors, to locomotion mode intent recognition in transfemoral amputees using powered prostheses. Additionally, we determined the effect of adding time history information using a dynamic Bayesian network (DBN) for both the Mechanical and EMG Sensors. Approach. EMG signals from the residual limbs of amputees have been proposed to enhance pattern recognition‐based intent recognition systems for powered lower limb prostheses, but Mechanical Sensors on the prosthesis—such as inertial measurement units, position and velocity Sensors, and load cells—may be just as useful. EMG and Mechanical Sensor data were collected from 8 transfemoral amputees using a powered knee/ankle prosthesis over basic locomotion modes such as walking, slopes and stairs. An offline study was conducted to determine the benefit of different Sensor sets for predicting intent. Main results. EMG information was not as accurate alone as Mechanical Sensor information (p < 0.05) for any classification strategy. However, EMG in combination with the Mechanical Sensor data did significantly reduce intent recognition errors (p < 0.05) both for transitions between locomotion modes and steady-state locomotion. The Sensor time history (DBN) classifier significantly reduced error rates compared to a linear discriminant classifier for steady-state steps, without increasing the transitional error, for both EMG and Mechanical Sensors. Combining EMG and Mechanical Sensor data with Sensor time history reduced the average transitional error from 18.4% to 12.2% and the average steady-state error from 3.8% to 1.0% when classifying level-ground walking, ramps, and stairs in eight transfemoral amputee subjects. Significance. These results suggest that a neural interface in combination with time history methods for locomotion mode classification can enhance intent recognition performance; this strategy should be considered for future real-time experiments.
-
A Training Method for Locomotion Mode Prediction Using Powered Lower Limb Prostheses
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2014Co-Authors: Aaron J. Young, Ann M. Simon, Levi J. HargroveAbstract:Recently developed lower-limb prostheses are capable of actuating the knee and ankle joints, allowing amputees to perform advanced locomotion modes such as step-over-step stair ascent and walking on sloped surfaces. However, transitions between these locomotion modes and walking are neither automatic nor seamless. This study describes methods for construction and training of a high-level intent recognition system for a lower-limb prosthesis that provides natural transitions between walking, stair ascent, stair descent, ramp ascent, and ramp descent. Using Mechanical Sensors onboard a powered prosthesis, we collected steady-state and transition data from six transfemoral amputees while the five locomotion modes were performed. An intent recognition system built using only Mechanical Sensor data was 84.5% accurate using only steady-state training data. Including training data collected while amputees performed seamless transitions between locomotion modes improved the overall accuracy rate to 93.9%. Training using a single analysis window at heel contact and toe off provided higher recognition accuracy than training with multiple analysis windows. This study demonstrates the capability of an intent recognition system to provide automatic, natural, and seamless transitions between five locomotion modes for transfemoral amputees using powered lower limb prostheses.
Aaron Young - One of the best experts on this subject based on the ideXlab platform.
-
real time gait phase estimation for robotic hip exoskeleton control during multimodal locomotion
International Conference on Robotics and Automation, 2021Co-Authors: Inseung Kang, Dean D Molinaro, Srijan Duggal, Yanrong Chen, Pratik Kunapuli, Aaron YoungAbstract:We developed and validated a gait phase estimator for real-time control of a robotic hip exoskeleton during multimodal locomotion. Gait phase describes the fraction of time passed since the previous gait event, such as heel strike, and is a promising framework for appropriately applying exoskeleton assistance during cyclic tasks. A conventional method utilizes a Mechanical Sensor to detect a gait event and uses the time since the last gait event to linearly interpolate the current gait phase. While this approach may work well for constant treadmill walking, it shows poor performance when translated to overground situations where the user may change walking speed and locomotion modes dynamically. To tackle these challenges, we utilized a convolutional neural network-based gait phase estimator that can adapt to different locomotion mode settings to modulate the exoskeleton assistance. Our resulting model accurately predicted the gait phase during multimodal locomotion without any additional information about the user's locomotion mode, with a gait phase estimation RMSE of 5.04 $\pm$ 0.79%, significantly outperforming the literature standard ( p $ 0.05). Our study highlights the promise of translating exoskeleton technology to more realistic settings where the user can naturally and seamlessly navigate through different terrain settings.
-
analysis of using emg and Mechanical Sensors to enhance intent recognition in powered lower limb prostheses
Journal of Neural Engineering, 2014Co-Authors: Aaron Young, Levi J. Hargrove, Todd A KuikenAbstract:Objective. The purpose of this study was to determine the contribution of electromyography (EMG) data, in combination with a diverse array of Mechanical Sensors, to locomotion mode intent recognition in transfemoral amputees using powered prostheses. Additionally, we determined the effect of adding time history information using a dynamic Bayesian network (DBN) for both the Mechanical and EMG Sensors. Approach. EMG signals from the residual limbs of amputees have been proposed to enhance pattern recognition‐based intent recognition systems for powered lower limb prostheses, but Mechanical Sensors on the prosthesis—such as inertial measurement units, position and velocity Sensors, and load cells—may be just as useful. EMG and Mechanical Sensor data were collected from 8 transfemoral amputees using a powered knee/ankle prosthesis over basic locomotion modes such as walking, slopes and stairs. An offline study was conducted to determine the benefit of different Sensor sets for predicting intent. Main results. EMG information was not as accurate alone as Mechanical Sensor information (p < 0.05) for any classification strategy. However, EMG in combination with the Mechanical Sensor data did significantly reduce intent recognition errors (p < 0.05) both for transitions between locomotion modes and steady-state locomotion. The Sensor time history (DBN) classifier significantly reduced error rates compared to a linear discriminant classifier for steady-state steps, without increasing the transitional error, for both EMG and Mechanical Sensors. Combining EMG and Mechanical Sensor data with Sensor time history reduced the average transitional error from 18.4% to 12.2% and the average steady-state error from 3.8% to 1.0% when classifying level-ground walking, ramps, and stairs in eight transfemoral amputee subjects. Significance. These results suggest that a neural interface in combination with time history methods for locomotion mode classification can enhance intent recognition performance; this strategy should be considered for future real-time experiments.
Gérard André Capolino - One of the best experts on this subject based on the ideXlab platform.
-
shaft positioning for six phase induction machines with open phases using variable structure control
IEEE Transactions on Industrial Electronics, 2012Co-Authors: F Betin, Gérard André CapolinoAbstract:In this paper, a new variable structure control law is proposed in order to obtain the shaft positioning of a symmetrical six-phase induction machine when phases are lost and when large variations of inertia occur. The algorithm based on a time-varying switching line guarantees the existence of a sliding mode since the beginning of the shaft motion. Indeed, the surface is first designed to pass through the initial representative point and, subsequently, to move toward a predetermined desired surface via shifting. With this algorithm, the induction machine behavior is exactly the same in healthy or in faulted modes when one or more stator phases are lost and whatever the Mechanical shaft configuration is. The capacities of this control technique with a Mechanical Sensor have been tested in simulation and then validated experimentally on a specific setup.
-
Torsional-vibration assessment and gear-fault diagnosis in railway traction system
IEEE Transactions on Industrial Electronics, 2011Co-Authors: Humberto Henao, Shahin Hedayati Kia, Gérard André CapolinoAbstract:The diagnosis of Mechanical faults in railway traction systems (RTSs) has a significant importance on both safety and reliability, which can avoid train crashes. This papaer deals with torsional-vibration assessment and gear-fault diagnosis in the Mechanical transmission of a high-speed RTS by a fully noninvasive technique. Previous studies on a simple gearbox-based electroMechanical system have shown that the influence of gearbox torsional vibrations on the torque and on the stator-current signatures are obvious. The aim of this paper is to demonstrate that the traction motor can be considered as a torque Sensor through its electromagnetic-torque estimation for torsionalvibration monitoring without any extra Mechanical Sensor. The effects of both tooth-damage and surface-wear faults at the output wheel on the stator current and on the estimated electromagnetic torque have been investigated. The results of the estimation are compared with the measured Mechanical torque and validated through a reduced-scale RTS in both stationary and nonstationary conditions.
-
torsional vibration effects on induction machine current and torque signatures in gearbox based electroMechanical system
IEEE Transactions on Industrial Electronics, 2009Co-Authors: Humberto Henao, Gérard André CapolinoAbstract:The monitoring of heavy-duty electroMechanical systems is crucial for their preventive maintenance planning. In these systems, the Mechanical anomalies such as load troubles, great torque dynamic variations, and torsional oscillations lead to shaft fatigue and aging of other Mechanical parts such as bearings and gearboxes. In this paper, a gearbox-based electroMechanical system is investigated. Initially, a simple gearbox dynamic model is used to show the effects of rotating input, output, and mesh frequency components on the electromagnetic torque and consequently on the stator current signature. By this model, the influence of transmission error, eccentricities of pinion/wheel, and teeth contact stiffness variation is demonstrated for a healthy gearbox. Then, it is shown that the electrical machine can be considered as a torque Sensor through electromagnetic torque estimation for torsional vibration monitoring without any extra Mechanical Sensor. A test-rig based on a 5.5-kW three-phase squirrel-cage induction motor connected to a wound-rotor 4-kW induction generator via a one-stage gearbox has been used to validate the proposed method.
Ann M. Simon - One of the best experts on this subject based on the ideXlab platform.
-
Online adaptive neural control of a robotic lower limb prosthesis.
Journal of neural engineering, 2018Co-Authors: John A. Spanias, Ann M. Simon, Suzanne B. Finucane, Eric J. Perreault, Levi J. HargroveAbstract:Objective The purpose of this study was to develop and evaluate an adaptive intent recognition algorithm that continuously learns to incorporate a lower limb amputee's neural information (acquired via electromyography (EMG)) as they ambulate with a robotic leg prosthesis. Approach We present a powered lower limb prosthesis that was configured to acquire the user's neural information and kinetic/kinematic information from embedded Mechanical Sensors, and identify and respond to the user's intent. We conducted an experiment with eight transfemoral amputees over multiple days. EMG and Mechanical Sensor data were collected while subjects using a powered knee/ankle prosthesis completed various ambulation activities such as walking on level ground, stairs, and ramps. Our adaptive intent recognition algorithm automatically transitioned the prosthesis into the different locomotion modes and continuously updated the user's model of neural data during ambulation. Main results Our proposed algorithm accurately and consistently identified the user's intent over multiple days, despite changing neural signals. The algorithm incorporated 96.31% [0.91%] (mean, [standard error]) of neural information across multiple experimental sessions, and outperformed non-adaptive versions of our algorithm-with a 6.66% [3.16%] relative decrease in error rate. Significance This study demonstrates that our adaptive intent recognition algorithm enables incorporation of neural information over long periods of use, allowing assistive robotic devices to accurately respond to the user's intent with low error rates.
-
Effect of additional Mechanical Sensor data on an EMG-based pattern recognition system for a powered leg prosthesis
2015 7th International IEEE EMBS Conference on Neural Engineering (NER), 2015Co-Authors: John A. Spanias, Ann M. Simon, Kimberly A. Ingraham, Levi J. HargroveAbstract:Powered lower limb prostheses can improve amputees' ability to traverse stairs and ramps by providing positive Mechanical work at the knee and ankle joint. EMG signals have been proposed as one way of providing seamless mode transitions by using them in combination with embedded Mechanical Sensors as inputs to a pattern recognition system that predicts the user's desired locomotion mode. In this study, we have expanded the amount of Mechanical Sensor information to include data from an additional five degrees of freedom in the load cell, as well as calculated thigh and shank angles. The purpose of this study was to determine the impact of this additional information on the performance of an EMG-based pattern recognition system designed to predict the desired locomotion mode. Our results indicate that including the additional Mechanical Sensor signals decreased the error rates of the system for both steady-state and transitional steps when compared to the reduced Sensor set. We also found that EMG still decreased the error rate of the system, but to a lesser extent when using the additional Mechanical Sensors.
-
A Training Method for Locomotion Mode Prediction Using Powered Lower Limb Prostheses
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2014Co-Authors: Aaron J. Young, Ann M. Simon, Levi J. HargroveAbstract:Recently developed lower-limb prostheses are capable of actuating the knee and ankle joints, allowing amputees to perform advanced locomotion modes such as step-over-step stair ascent and walking on sloped surfaces. However, transitions between these locomotion modes and walking are neither automatic nor seamless. This study describes methods for construction and training of a high-level intent recognition system for a lower-limb prosthesis that provides natural transitions between walking, stair ascent, stair descent, ramp ascent, and ramp descent. Using Mechanical Sensors onboard a powered prosthesis, we collected steady-state and transition data from six transfemoral amputees while the five locomotion modes were performed. An intent recognition system built using only Mechanical Sensor data was 84.5% accurate using only steady-state training data. Including training data collected while amputees performed seamless transitions between locomotion modes improved the overall accuracy rate to 93.9%. Training using a single analysis window at heel contact and toe off provided higher recognition accuracy than training with multiple analysis windows. This study demonstrates the capability of an intent recognition system to provide automatic, natural, and seamless transitions between five locomotion modes for transfemoral amputees using powered lower limb prostheses.
Roque Saltaren - One of the best experts on this subject based on the ideXlab platform.
-
alice conceptual development of a lower limb exoskeleton robot driven by an on board musculoskeletal simulator
Sensors, 2020Co-Authors: Manuel Cardona, Cecilia Garcia E Cena, Fernando E Serrano, Roque SaltarenAbstract:Objective: In this article, we present the conceptual development of a robotics platform, called ALICE (Assistive Lower Limb Controlled Exoskeleton), for kinetic and kinematic gait characterization. The ALICE platform includes a robotics wearable exoskeleton and an on-board muscle driven simulator to estimate the user’s kinetic parameters. Background: Even when the kinematics patterns of the human gait are well studied and reported in the literature, there exists a considerable intra-subject variability in the kinetics of the movements. ALICE aims to be an advanced Mechanical Sensor that allows us to compute real-time information of both kinetic and kinematic data, opening up a new personalized rehabilitation concept. Methodology: We developed a full muscle driven simulator in an open source environment and validated it with real gait data obtained from patients diagnosed with multiple sclerosis. After that, we designed, modeled, and controlled a 6 DoF lower limb exoskeleton with inertial measurement units and a position/velocity Sensor in each actuator. Significance: This novel concept aims to become a tool for improving the diagnosis of pathological gait and to design personalized robotics rehabilitation therapies. Conclusion: ALICE is the first robotics platform automatically adapted to the kinetic and kinematic gait parameters of each patient.