Creating Human-Like Facial Expressions Utilizing Artificial Muscles and Skin

Abstract

Mimicking facial structures for a robotic head requires integration of multiple structural and mechanical parameters, design, synthesis and control of muscle actuation, architecture of the linkages between actuation points within skin, and implementation of the deformation matrix with respect to global skull coordinates. In this dissertation, humanoid faces were designed and fabricated to investigate all the parameters mentioned above. A prototype face and neck was developed using servo motors and extensively characterized. In this prototype, a neck mechanism was designed using a four bar mechanism to achieve nodding and turning motions. The modular neck prototype simplifies the assembly and statically in equilibrium and hence demands less torque from the cost-effective RC servo motor. The mechanism was critically investigated for dynamic performance and it was found out that RC servo based robotic head requires a PD external controller to overcome inherent overshoot. The servo based robotic head was analyzed for design and control of anchor, architecture of linkages between actuation points within skin, and deformation matrix with respect to global coordinate for creating specific expressions. A functional relationship between deformation vector of facial control points and actuator parameter, skin elasticity and angular position of actuator was derived. The developed analysis method is applicable to any rotary actuator technology utilized for facial expressions and takes into account the skin stiffness. The artificial skin materials for facial expression were synthesized using platinum-cured silicone elastomeric material (Reynolds Advanced Materials Inc.) with base consisting of mainly polyorganosiloxanes, amorphous silica and platinum-siloxane complex compounds. Systematic incorporation of porosity in this material was found to lower the force required to deform the skin in the axial direction. The performance of the servo motor based face was quite realistic but it suffers from the drawback of large power consumption, bulky, heavy, and limited functionality. Thus, significant effort was made in developing a Biometal fiber and Flexinol shape memory alloy actuator (SMA) based biped mountable baby head facial structure which resembles the form and functionality of a human being. SMAs were embedded inside a skull and connected to elastomeric skin at control points. An engineered architecture of skull was fabricated that incorporates all the muscles with their 35 routine pulleys, two fire wire CMOS cameras that serve as eyes, and a battery powered microcontroller base driving circuit within the total dimensions of 140 mm x 90 mm x 110 mm. The driving circuit was designed such that it can be easily integrated with biped and processed in real-time. The humanoid face with 12DOF was mounted on the body of DARwIn (Dynamic Anthropomorphic Robot with Intelligence) robot which has 21 DOF resulting in a total of 33 DOF system. Characterization results on the face and associated design issues are described that provide pathways for developing human-like facial anatomy. Numerical simulation using Simulink was conducted to assess the performance of a prototypic robotic face mainly focusing on jaw movement. A graphical method “Graphical Facial Expression Analysis and Design (GFEAD)” was developed that can be used to allocate the sinking points on robotic head. The method assumes that the origin of the action units are known prior and the underlying criterion in the design of faces being deformation of a soft elastomeric skin through tension in anchoring wires attached on one end to the sinking point and on the other to the actuator. Experimental characterization on a prototyping humanoid face was performed to validate the model and demonstrate the applicability on a generic platform. During characterization of the SMA based face, it was found that the currently available artificial muscle technologies do not meet the entire requirement for