Gait-pattern adaptation algorithms based on neural network for lower limbs active orthoses

Gomes, Marciel A.; Silveira, Guilherme L. M.; Siqueira, Adriano A. G.

doi:10.1109/iros.2009.5354232

Cited by 14 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stepping approach is widely utilized in balance control for humanoid robots [18, 19] and exoskeletons [11, 12, 20]. MINDWALKER [11, 12] is a powered lower-limb exoskeleton designed for paraplegics to regain locomotion capability.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Balance Gait for Walking Assistance Exoskeleton

Chen

Cheng

Yue

et al. 2018

Applied Bionics and Biomechanics

View full text Add to dashboard Cite

Purpose Powered lower-limb exoskeleton has gained considerable interests, since it can help patients with spinal cord injury(SCI) to stand and walk again. Providing walking assistance with SCI patients, most exoskeletons are designed to follow predefined gait trajectories, which makes the patient walk unnaturally and feels uncomfortable. Furthermore, exoskeletons with predefined gait trajectories cannot always maintain balance walking especially when encountering disturbances. Design/Methodology/Approach This paper proposed a novel gait planning approach, which aims to provide reliable and balance gait during walking assistance. In this approach, we model the exoskeleton and patient together as a linear inverted pendulum (LIP) and obtain the patients intention through orbital energy diagram. To achieve dynamic gait planning of exoskeleton, the dynamic movement primitive (DMP) is utilized to model the gait trajectory. Meanwhile, the parameters of DMP are updated dynamically during one step, which aims to improve the ability of counteracting external disturbance. Findings The proposed approach is validated in a human-exoskeleton simulation platform, and the experimental results show the effectiveness and advantages of the proposed approach. Originality/Value We decomposed the issue of obtain dynamic balance gait into three parts: (1) based on the sensory information of exoskeleton, the intention estimator is designed to estimate the intention of taking a step; (2) at the beginning of each step, the discrete gait planner utilized the obtained gait parameters such as step length S and step duration T and generate the trajectory of swing foot based on (S, T); (3) during walking process, continuous gait regulator is utilized to adjust the gait generated by discrete gait planner to counteract disturbance.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…In [20], gait planning for balance is based on ZMP. 7-links model [21] is utilized to model exoskeleton.…”

Section: Literature Reviewmentioning

confidence: 99%

Dynamic Balance Gait for Walking Assistance Exoskeleton

Chen

Cheng

Yue

et al. 2018

Applied Bionics and Biomechanics

View full text Add to dashboard Cite

show abstract

“…The exoskeleton being developed [16] is based on a LSU (Lousiana State University) reciprocating gait orthosis. The design of the exoskeleton with the position of the actuators with relation to the orthosis and the drive mechanisms of each joint is shown in Figure 1.…”

Section: Active Ankle-foot Orthosismentioning

confidence: 99%

Sensor fusion applied to position estimation and gait identification of an ankle-foot orthosis

Caltran

Siqueira

2011

ISSNIP Biosignals and Biorobotics Conference 2011

Self Cite

View full text Add to dashboard Cite

This paper presents a sensor fusion strategy to estimate the absolute position and to identify the gait events of an active ankle-foot orthosis (AAFO). Sensor fusion is implemented using a Kalman filter with the signals of a gyroscope and an accelerometer, both present in an inertial measurement unit (IMU), besides the signals of three force sensitive resistors (FSRs) mounted in a sole of shoe. For correcting the gyroscopebased position, the redundant accelerometer-based position must be used only under reliable conditions, which are obtained by a proposed switching logic to enable the Kalman filter. Experimental results of the AAFO confirm the efficiency of the proposed sensor fusion strategy.

show abstract

“…Neural networks compose of simple elements operating in parallel [7][8][9][10][11][12]. These elements are inspired by biological nervous systems.…”

Section: Neural Networkmentioning

confidence: 99%

“…Most gait analyses work in time domain [1], [9][10][11][12][13]. Different walking speed can affect system performance.…”

mentioning

confidence: 99%

Neural-based human's abnormal gait detection using Force Sensitive Resistors

Pawin

Khaorapapong

Chawalit

2011

The Fourth International Workshop on Advanced Computational Intelligence

View full text Add to dashboard Cite

Abnormal gait leads to falling which can cause of human's injury. Normally human has resembled gait cycle between walking. But if human has falling or abnormal walking that gait cycle is not resemble the normal walking. The walking gait can calculate the locus of the Zero Moment Point (ZMP) and the ZMP can be estimated by the signal from low-cost Force Sensitive Resistors (FSRs) . Four FSRs were installed in the sole of a shoe. This paper presents the detection of human's abnormal gait by using the FSRs signal. Artificial Neural Networks were applied to recognize ZMP locus of the normal gait cycle and use the trained neuron to classify the normal gait. Experimental data were recorded from 10 volunteers of age between 18-25 years, height 150-175 cm., and weight 40 -75 kg, The results show that the neural network can detect abnormal gait cycles.

show abstract

Gait-pattern adaptation algorithms based on neural network for lower limbs active orthoses

Cited by 14 publications

References 9 publications

Dynamic Balance Gait for Walking Assistance Exoskeleton

Dynamic Balance Gait for Walking Assistance Exoskeleton

Sensor fusion applied to position estimation and gait identification of an ankle-foot orthosis

Neural-based human's abnormal gait detection using Force Sensitive Resistors

Contact Info

Product

Resources

About