Online adaptive neural control of a robotic lower limb prosthesis

Spanias, John A.; Simon, Ann M.; Finucane, Suzanne B.; Perreault, Eric J.; Hargrove, Levi J.

doi:10.1088/1741-2552/aa92a8

Cited by 99 publications

(80 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system robustness is critical to accommodate for deviations from expected conditions. There are examples of long‐term users of A‐MPK‐A using surface electromyography (EMG) to interact with the onboard sensors of the prosthesis [68] to accurately respond to the user's intent.…”

Section: Discussionmentioning

confidence: 99%

Motorized Biomechatronic Upper and Lower Limb Prostheses—Clinically Relevant Outcomes

Lechler

Frossard

Whelan

et al. 2018

PM&R

View full text Add to dashboard Cite

People with major limb amputations are severely impaired when it comes to activity, body structure and function, as well as participation. Demographic statistics predict a dramatic increase of this population and additional challenges with their increasing age and higher levels of amputation. Prosthetic use has been shown to have a positive impact on mobility and depression, thereby affecting the quality of life. Biomechatronic prostheses are at the forefront of prosthetic development. Actively powered designs are now regularly used for upper limb prosthetic fittings, whereas for lower limbs the clinical use of actively powered prostheses has been limited to a very low number of applications. Actively powered prostheses enhance restoration of the lost physical functions of an amputee but are yet to allow intuitive user control. This paper provides a review of the status of biomechatronic developments in upper and lower limb prostheses in the context of the various challenges of amputation and the clinically relevant outcomes. Whereas most of the evidence regarding lower limb prostheses addresses biomechanical issues, the evidence for upper limb prostheses relates to activities of daily living (ADL) and instrumental ADL through diverse outcome measures and tools.

show abstract

Section: Discussionmentioning

confidence: 99%

Motorized Biomechatronic Upper and Lower Limb Prostheses—Clinically Relevant Outcomes

Lechler

Frossard

Whelan

et al. 2018

PM&R

View full text Add to dashboard Cite

show abstract

“…There is an opportunity to significantly increase the effectiveness of devices currently available by switching aim towards a more ambitious recreation of normal motor activity. Promising advancements in the field of prosthetics have demonstrated dynamic control of a powered lower-limb prosthetic using EMGs (Wen et al 2017;Spanias et al 2018). A similar approach used to control stimulation could create a system that directly integrates motor output into an FES device.…”

Section: Current Treatment Optionsmentioning

confidence: 99%

A survey on foot drop and functional electrical stimulation

York

Chakrabarty

2019

Int J Intell Robot Appl

View full text Add to dashboard Cite

The weakness of the lower leg muscles due to nerve damage or muscle weakness can result in foot drop, a change in gait that manifests as an inability to lift the toes of the foot when walking. Foot drop results in a decreased quality of life, with unassisted movement becoming difficult or impossible. The increased risk of falls is particularly problematic as foot drop often affects the elderly or infirm for whom falling already presents a great danger. Current treatment options include fixed ankle-foot orthosis (AFO) aiming to provide rigid support to the foot if the impairment is mild or surgical intervention and functional electrical stimulation (FES) devices if the weakness is more severe. FES intervention is effective for providing a non-invasive treatment in even severe cases of foot drop. Limitations of current models relate to the non-naturalistic recreation of gait in the affected leg and its unsuitability for patients with extensive peripheral nerve damage. Although there are attempts to enhance integration of sensory information and mimic natural stimulation patterns, the focus on restoring a natural feedback loop is still amiss. Without such a closed loop feedback, restoration of a natural gait pattern is unlikely to occur. We here recommend, integration of motor output from multiple muscles, information about the inputs from higherorder controllers, recorded from the intact leg with a closed loop system to improve the effectiveness of FES.

show abstract

“…Furthermore, they tried on-line recognition (on Matlab) based on sEMG and mechanical sensors with powered prosthetics (Zhang et al, 2015). Hargrove et al have also developed on-line recognition by fusing sEMG and mechanical sensors (Spanias et al, 2016(Spanias et al, , 2018. We have also developed realtime on-board recognition of continuous locomotion modes for amputees with robotic transtibial prostheses and got more than 93% recognition accuracy with just two IMUs (Xu et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

“…Off-line training means bringing in other devices (e.g., a computer) to train the model, which is not convenient in integration with robotic prosthetics (Zhang et al, 2015;Xu et al, 2018). To improve the problem, Spanias et al (2018) conducted a model updated on an embedded micro-controller based on mechanical sensor and sEMG. However, the multi-type sensors fusion method may bring wearing difficulty for amputees and integration difficulty for the prosthesis.…”

Section: Introductionmentioning

confidence: 99%

On-board Training Strategy for IMU-Based Real-Time Locomotion Recognition of Transtibial Amputees With Robotic Prostheses

Wang

2020

Front. Neurorobot.

View full text Add to dashboard Cite

The paper puts forward an on-board strategy for a training model and develops a real-time human locomotion mode recognition study based on a trained model utilizing two inertial measurement units (IMUs) of robotic transtibial prosthesis. Three transtibial amputees were recruited as subjects in this study to finish five locomotion modes (level ground walking, stair ascending, stair descending, ramp ascending, and ramp descending) with robotic prostheses. An interaction interface was designed to collect sensors' data and instruct to train model and recognition. In this study, the analysis of variance ratio (no more than 0.05) reflects the good repeatability of gait. The on-board training time for SVM (Support Vector Machines), QDA (Quadratic Discriminant Analysis), and LDA (Linear discriminant analysis) are 89, 25, and 10 s based on a 10,000 × 80 training data set, respectively. It costs about 13.4, 5.36, and 0.067 ms for SVM, QDA, and LDA for each recognition process. Taking the recognition accuracy of some previous studies and time consumption into consideration, we choose QDA for real-time recognition study. The real-time recognition accuracies are 97.19 ± 0.36% based on QDA, and we can achieve more than 95% recognition accuracy for each locomotion mode. The receiver operating characteristic also shows the good quality of QDA classifiers. This study provides a preliminary interaction design for human-machine prosthetics in future clinical application. This study just adopts two IMUs not multi-type sensors fusion to improve the integration and wearing convenience, and it maintains comparable recognition accuracy with multi-type sensors fusion at the same time.

show abstract

Online adaptive neural control of a robotic lower limb prosthesis

Abstract: 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.

Cited by 99 publications

References 43 publications

Motorized Biomechatronic Upper and Lower Limb Prostheses—Clinically Relevant Outcomes

Motorized Biomechatronic Upper and Lower Limb Prostheses—Clinically Relevant Outcomes

A survey on foot drop and functional electrical stimulation

On-board Training Strategy for IMU-Based Real-Time Locomotion Recognition of Transtibial Amputees With Robotic Prostheses

Contact Info

Product

Resources

About