EMG-based hand gesture recognition for realtime biosignal interfacing
Proceedings of the 13th international conference on Intelligent user interfaces
ROBIO '09 Proceedings of the 2008 IEEE International Conference on Robotics and Biomimetics
| Hi-index | 0.00 |
The aim of this work was to design and demonstrate a dexterous anthropomorphic mobile robotic arm with nine degrees of freedom using readily available low-cost components to perform different object-picking tasks for immobile patients in developing nations. The robotic arm consists of a shoulder, elbow, wrist and five-finger gripper. It can perform different gripping actions, such as lateral, spherical, cylindrical and tip-holding gripping actions using a five-finger gripper; each finger has three movable links. The actuator used for the robotic arm is a high torque dc motor coupled with a gear assembly for torque amplification, and the five-finger gripper consists of five cables placed like tendons in the human arm. The robotic arm utilizes a controller at every link to trace the desired trajectory with high accuracy and precision. Digital implementation of the control algorithm is done on an Atmel Atmega-16 microcontroller using trapezoidal approximation and Newton's backward difference methods. The arm can be programmed or controlled manually to perform a variety of object-picking tasks. A prototype of the robotic arm was constructed, and test results on a variety of object-picking tasks are presented.