Robust Fusion Model for Handling EMG and Computer Vision Data in Prosthetic Hand Control

Deshmukh, S. M.; Khatik, Vitthal; Saxena, Anupam

doi:10.1109/lsens.2023.3301837

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the accuracy values in grasp classification are higher than or generally consistent with what has been observed in the literature [17,19], despite a substantial increase in the number of grasps [20,34] and the management of the prosthetic wrist orientation [21,22].…”

Section: Resultssupporting

confidence: 86%

“…Recent studies explored the use of a multimodal system with EMG and CVS in prosthetic control [20,21], proposing a strategy for combining these two types of information to improve the accuracy with respect to an EMG classifier. The hand gesture determined based on information gathered from an environmental CVS was used as an additional feature alongside those extracted from EMG signals to infer the final grasp to be executed [22], neglecting wrist orientation. From the state-of-the-art analysis, the need for a novel SCS that manages both hand and wrist configuration by simultaneously taking into account the user's motion intention is therefore evident.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Semiautonomous Control Strategy Based on Computer Vision for a Hand–Wrist Prosthesis

Cirelli,

Tamantini,

Cordella

et al. 2023

Robotics

View full text Add to dashboard Cite

Alleviating the burden on amputees in terms of high-level control of their prosthetic devices is an open research challenge. EMG-based intention detection presents some limitations due to movement artifacts, fatigue, and stability. The integration of exteroceptive sensing can provide a valuable solution to overcome such limitations. In this paper, a novel semiautonomous control system (SCS) for wrist–hand prostheses using a computer vision system (CVS) is proposed and validated. The SCS integrates object detection, grasp selection, and wrist orientation estimation algorithms. By combining CVS with a simulated EMG-based intention detection module, the SCS guarantees reliable prosthesis control. Results show high accuracy in grasping and object classification (≥97%) at a fast frame analysis frequency (2.07 FPS). The SCS achieves an average angular estimation error ≤18° and stability ≤0.8° for the proposed application. Operative tests demonstrate the capabilities of the proposed approach to handle complex real-world scenarios and pave the way for future implementation on a real prosthetic device.

show abstract