GESTURE CONTROL OF A ROBOTIC ARM AND HAND (UHAND) WITH COMPUTER VISION BASED SYSTEM
Abstract
This project presents the design and implementation of a vision-based system that
lets users control a robotic arm and robotic hand (UHAND) using simple hand
gestures. With MediaPipe’s pose and hand tracking models, a Raspberry Pi 4
processes video from a webcam, reads hand movements, and sends commands to
servos through a PCA9685 driver. The setup includes five servos for the arm and
five more for the UHAND’s fingers. ROS 2 handles communication between the
gesture system and the hardware. In testing, the system achieved around 94.2%
gesture recognition accuracy with response times under 200 milliseconds, making
the control feel smooth and responsive. The results show real potential for use in
assistive tech, interactive systems, and robotics education, offering a flexible and
modular solution built on accessible tools.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.