Human Head and Eye Imitation Robot

Overview

Investigated approaches to extract meaningful information from face mesh data for realistic facial mimicry. Utilized a 3DOF agile eye parallel robot to simulate human neck movements with three degrees of freedom. Fabricated 2DOF animatronic eyes using SolidWorks and 3D printed parts.

Key Contributions

• Explored computer vision and neural networks for human face pose estimation
• Used linear regression and other methods for pose calculation
• Built a complete animatronic system combining neck and eye movements

Technologies

Python, Mediapipe, C, OpenCV, ROS, Arduino, SolidWorks

Related Paper

• Experimental Study on the Imitation of the Human Head-and-Eye Pose Using the 3-DOF Agile Eye Parallel Robot — IEEE ICRoM 2021