Towards Creating a Deployable Grasp Type Probability Estimator for a Prosthetic Hand

TL;DR

This paper proposes a machine learning approach combining visual data and probabilistic labels to improve grasp type prediction for prosthetic hands, enhancing robustness over traditional EMG-based methods.

Contribution

It introduces a novel probabilistic labeling scheme and evaluates deep neural networks for integrating visual and EMG data in prosthetic grasp prediction.

Findings

InceptionV3 achieved 0.95 angular similarity.

MobileNetV2 achieved 0.93 angular similarity.

Proposed method improves grasp prediction accuracy.

Abstract

For lower arm amputees, prosthetic hands promise to restore most of physical interaction capabilities. This requires to accurately predict hand gestures capable of grabbing varying objects and execute them timely as intended by the user. Current approaches often rely on physiological signal inputs such as Electromyography (EMG) signal from residual limb muscles to infer the intended motion. However, limited signal quality, user diversity and high variability adversely affect the system robustness. Instead of solely relying on EMG signals, our work enables augmenting EMG intent inference with physical state probability through machine learning and computer vision method. To this end, we: (1) study state-of-the-art deep neural network architectures to select a performant source of knowledge transfer for the prosthetic hand, (2) use a dataset containing object images and probability distribution of grasp types as a new form of labeling where instead of using absolute values of zero and one as the conventional classification labels, our labels are a set of probabilities whose sum is 1. The proposed method generates probabilistic predictions which could be fused with EMG prediction of probabilities over grasps by using the visual information from the palm camera of a prosthetic hand. Our results demonstrate that InceptionV3 achieves highest accuracy with 0.95 angular similarity followed by 1.4 MobileNetV2 with 0.93 at ~20% the amount of operations.