Comparing Pre-Trained Object Detection Models for Autonomous Grasp on Affordable Prosthetic Hands

While prosthetic technology has advanced significantly in recent years, discomfort, poor fit, and functional limitations still contribute to high rejection rates among users who feel more efficient without the prosthesis. In the field of prosthetics, improving the stability of grasp and natural control is crucial for reducing rejection rates. By improving these aspects, the user can reduce the likelihood of complications arising, such as discomfort or pain. The integration of vision technology, a novel prosthetic approach, holds immense promise for revolutionizing how we design and use prosthetic devices. Incorporating advanced vision algorithms into prosthetic devices can augment users' sensory capabilities and enhance their interaction with the surrounding environment. Vision-based prostheses offer the potential for more intuitive and natural control, enabling users to manipulate objects with greater precision and dexterity. This paper presents preliminary insights into rejection rates and the utilization of vision-based grasping in robotics, with implications for prosthetic applications. In this study, we investigate the performance of Mobilenet SSD, YOLOv5m, and YOLOv5l in autonomous grasp tasks across two distances, providing valuable data on their adaptability in real-world contexts. Our analysis delves into the effectiveness of vision-based grasping algorithms in grasp experiments with intact subjects, showing successful grasp attempts ranging from 84% to 92% in two different distances and three different grasp types.