ScholarWorks@중앙대학교

초록

This paper introduces a novel approach for prosthetic wrist control, addressing limitations of traditional electromyographybasedmethods. While previous research has primarily focused on hand and gripper development, our study emphasizesthe importance of wrist mobility for enhancing dexterity and manipulation skills. Leveraging a combination of visual data andinertial sensors, we proposed a system capable of estimating object orientation in real-time, enabling automatic and naturalcontrol of a prosthetic wrist. Our deep learning-based model can accurately interpret object posture from the user'sperspective, facilitating seamless wrist movement based on object inclination. In addition, Gaussian filtering was employedto mitigate noise in image-based posture estimation while preserving essential trends. Through this approach, users canachieve natural positioning without needing additional muscle movements, thus significantly improving prosthetic usabilityand user experience.

키워드