Bayesian human intention estimator for exoskeleton system

Cheng, Ching-An; Huang, Tzung-Chi; Huang, Han-Pang

doi:10.1109/aim.2013.6584135

Cited by 9 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the magnitude of human joint torque applied is unknown, estimation of human joint torque magnitude is critical, particularly in the control of assistive-type exoskeletons. Two methods are mainly used for human torque estimation in the literature: electromyography (EMG) and inverse dynamics methods [14]. EMG signals have been used in several research works to control assistive robots and estimate the human torque [14][15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

“…Two methods are mainly used for human torque estimation in the literature: electromyography (EMG) and inverse dynamics methods [14]. EMG signals have been used in several research works to control assistive robots and estimate the human torque [14][15][16][17][18]. Another type is electroencephalography (EEG), which is used to estimate the brain's motor activity in real time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sensorless Estimation of Human Joint Torque for Robust Tracking Control of Lower-Limb Exoskeleton Assistive Gait Rehabilitation

Abdullahi

Chaichaowarat

2023

JSAN

View full text Add to dashboard Cite

Patients suffering from motor disorders or weakness resulting from either serious spinal cord injury or stroke often require rehabilitation therapy to regain their mobility. In the lower limbs, exoskeletons have two motors aligned with the patients’ hip and knee to assist in rehabilitation exercises by supporting the patient’s body structure to increase the torques at the hip and knee joints. Assistive rehabilitation is, however, challenging, as the human torque is unknown and varies from patient to patient. This poses difficulties in determining the level of assistance required for a particular patient. In this paper, therefore, a modified extended state observer (ESO)-based integral sliding mode (ISM) controller (MESOISMC) for lower-limb exoskeleton assistive gait rehabilitation is proposed. The ESO is used to estimate the unknown human torque without application of a torque sensor while the ISMC is used to achieve robust tracking of preset hip and knee joint angles by considering the estimated human torque as a disturbance. The performance of the proposed MESOISMC was assessed using the mean absolute error (MAE). The obtained results show an 85.02% and 87.38% reduction in the MAE for the hip and joint angles, respectively, when the proposed MESOISMC is compared with ISMC with both controllers tuned via LMI optimization. The results also indicate that the proposed MESOISMC method is effective and efficient for user comfort and safety during gait rehabilitation training.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Sensorless Estimation of Human Joint Torque for Robust Tracking Control of Lower-Limb Exoskeleton Assistive Gait Rehabilitation

Abdullahi

Chaichaowarat

2023

JSAN

View full text Add to dashboard Cite

show abstract

Human Gait Trajectory Learning Using Online Gaussian Process for Assistive Lower Limb Exoskeleton

Long

Dong

et al. 2016

Wearable Sensors and Robots

View full text Add to dashboard Cite

A novel approach to motion tracking with wearable sensors based on Probabilistic Graphical Models

Ruffaldi

Peppoloni

Filippeschi

et al. 2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Wearable motion tracking systems represent a breakthrough in ecological motion tracking. Their effectiveness has been proved in many fields, from performance assessment to human-robot interaction. Most of the approaches are based on the exploitation of optimal probabilistic filtering of inertial motion units (IMUs) signals, ranging from linear Kalman Filters (KF) to Particle filters (PF). Since most of the models are highly nonlinear, filters such as Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) are typically used. These approaches cause all the variables of the models to be correlated each other. Probabilistic Graphical Models (PGM) are a framework for probabilistic reasoning that allows to explicitly declare the actual dependencies among variables. In this paper we propose a novel algorithm for motion tracking with IMUs based on PGM. The model is compared to the state of the art UKF algorithm in tracking the human upper limb. The results show that the proposed approach perform a slightly better compared to the UKF

show abstract

Bayesian human intention estimator for exoskeleton system

Cited by 9 publications

References 14 publications

Sensorless Estimation of Human Joint Torque for Robust Tracking Control of Lower-Limb Exoskeleton Assistive Gait Rehabilitation

Sensorless Estimation of Human Joint Torque for Robust Tracking Control of Lower-Limb Exoskeleton Assistive Gait Rehabilitation

Human Gait Trajectory Learning Using Online Gaussian Process for Assistive Lower Limb Exoskeleton

A novel approach to motion tracking with wearable sensors based on Probabilistic Graphical Models

Contact Info

Product

Resources

About