Comparative study of state-of-the-art myoelectric controllers for multigrasp prosthetic hands

Segil, Jacob L.; Controzzi, Marco; Weir, Richard F.; Cipriani, Christian

doi:10.1682/jrrd.2014.01.0014

Cited by 28 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hand gesture recognition based on forearm EMG signals is an enabling technology for the development of advanced and intuitive interaction strategies [4]. Its application to the development of naturally-controlled poliarticulated hand prosthesis is an interesting research challenge with promising results and the potential to dramatically improve the quality of life for forearm amputees [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Exploring Arm Posture and Temporal Variability in Myoelectric Hand Gesture Recognition

Milosevic¹,

Farella²,

Benaui

2018

2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob)

View full text Add to dashboard Cite

Hand gesture recognition based on myoelectric (EMG) signals is an innovative approach for the development of intuitive interaction devices, ranging from poliarticulated prosthetic hands to intuitive robot and mobile interfaces. Their study and development in controlled environments provides promising results, but effective real-world adoption is still limited due to reliability problems, such as motion artifacts and arm posture, temporal variability and issues caused by the re-positioning of sensors at each use. In this work, we present an EMG dataset collected with the aim to explore postural and temporal variability in the recognition of arm gestures. Its collection of gestures executed in 4 arm postures over 8 days allows to evaluate the impact of such variability on classification performance. We implemented and tested Stateof-the-Art (SoA) recognition approaches analyzing the impact of different training strategies. Moreover, we compared the computational and memory requirements of the considered algorithms, providing an additional evaluation criteria useful for real-time implementation. Results show a decrease in the recognition of inter-posture and inter-day gestures up to 20%. The provided dataset will allow further exploration of such effects and the development of effective training and recognition strategies.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploring Arm Posture and Temporal Variability in Myoelectric Hand Gesture Recognition

Milosevic¹,

Farella²,

Benaui

2018

2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob)

View full text Add to dashboard Cite

show abstract

“…However, although the number of available independent digits and movements have increased, the way these digits and movements are controlled by the user's intent is still practically unchanged with respect to earlier systems (cf. the work by Segil and colleagues for a review [18]). One of the main issues faced by HMI research is to allow the individual to control multiple DoFs simultaneously in order to allow arbitrary movements.…”

Section: Introductionmentioning

confidence: 99%

Is it Finger or Wrist Dexterity That is Missing in Current Hand Prostheses?

Montagnani

Controzzi

Cipriani

2015

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

113

View full text Add to dashboard Cite

Building prostheses with dexterous motor function equivalent to that of the human hand is one of the ambitious goals of bioengineers. State of art prostheses lack several degrees of freedom (DoF) and force the individuals to compensate for them by changing the motions of their arms and body. However, such compensatory movements often result in residual limb pain and overuse syndromes. Significant efforts were spent in designing artificial hands with multiple allowed grasps but little work has been done with regards to wrist design, regardless the fact that the wrist contributes significantly to the execution of upper limb motor tasks. We hypothesized that a single DoF hand with wrist flexion/extension allowed function comparable to a highly performant multi DoF hand without wrist flexion/extension. To assess this we compared four emulated architectures of hand-wrist prostheses using the Southampton Hand Assessment Procedure and evaluating the extent of compensatory movements with unimpaired subjects wearing ortheses. Our findings show indeed that shifting the dexterity from the hand to the wrist could preserve the ability of transradial amputees in performing common tasks with limited effect on the compensatory movements. Hence, this study invites rehabilitation engineers to focus on novel artificial wrist architectures.

show abstract

“…Figure 3f, 4c shows the distribution of hold times per object and per subject with or without shared control. We define hold time as the length of continuous time during which the subject could maintain required contacts between the virtual hand and object without any contacts being broken 25 .Due to the visual cue, a small percentage of non-hold time is likely due to subject reaction time. For all objects and subjects, hold times are greater with the shared control condition than only MLP, with the exception of the cylinder for subject B2.This may be due to the low number of trials subject B2 performed in comparison to Subjects A1-3.…”

Section: Resultsmentioning

confidence: 99%

Shared human–robot proportional control of a dexterous myoelectric prosthesis

et al. 2019

View full text Add to dashboard Cite

Myoelectric prostheses allow users to recover lost functionality by controlling a robotic device with their remaining muscle activity. Such commercial devices can give users a high level of autonomy, but still do not approach the dexterity of the intact human hand. We present here a method to control a robotic hand, shared between user intention and robotic automation. The algorithm allows user-controlled movements when high dexterity is desired, but also assisted grasping when robustness is paramount. This combination of features is currently lacking in commercial prostheses and can greatly improve prosthesis usability. First, we design and test a myoelectric proportional controller that can predict multiple joint angles simultaneously and with high accuracy. We then implement online control with both able-bodied and amputee subjects. Finally, we present a shared control scheme in which robotic automation aids in object grasping by maximizing contact area between hand and object, greatly increasing grasp success and object hold times in both a virtual and a physical environment. Our results present a viable method of prosthesis control implemented in real time, for reliable articulation of multiple simultaneous degrees of freedom. In the United States alone, about 1.6 million people live with an amputation, 541,000 of which affect the upper limbs 1. This condition diminishes quality of life, mobility and independence, while also imparting a social stigma 2. Upper limb prostheses controlled using surface electromyographic (sEMG) signals attempt to restore hand and arm functionality by using the amputee's remaining muscle activity to control movements of a prosthetic device. However, the capabilities of current commercial prostheses are still grossly inferior compared to the dexterity of the human hand. Commercial devices usually use a two-recording-channel system to control a single degree of freedom (DoF), i.e. one sEMG channel for flexion and one for extension 3. While intuitive, the system provides little dexterity. Patients abandon myoelectric prostheses at high rates, in part because they feel that the level of control is insufficient to merit the price and complexity of these devices 4-6 In recent years, various research groups have made significant advances in myoelectric prosthesis control in laboratory and prototype environments. Many groups have demonstrated great success in grasp classification, which is a common approach for prosthesis control, but limits the user to a library of trained hand postures 7-10. However a few groups have now attempted to decode single finger movements 11-13. Despite high decoding accuracy, these studies showed results mainly from able-bodied subjects performing offline tests. With cited decoding performances of upwards of 90-95% for each method, we see a clear dichotomy between laboratory experiments and clinical viability, a point that is addressed by Jiang et al 14. The idea of "shared control", that is, automation of some portion of the motor command, is already a topic...

show abstract

Comparative study of state-of-the-art myoelectric controllers for multigrasp prosthetic hands

Cited by 28 publications

References 21 publications

Exploring Arm Posture and Temporal Variability in Myoelectric Hand Gesture Recognition

Exploring Arm Posture and Temporal Variability in Myoelectric Hand Gesture Recognition

Is it Finger or Wrist Dexterity That is Missing in Current Hand Prostheses?

Shared human–robot proportional control of a dexterous myoelectric prosthesis

Contact Info

Product

Resources

About