A Novel Algebraic Inverse Kinematics Based Approach to Gaze Control in Humanoid Robots

The vision system of humanoid robots is one the essential components that allow them to do complex activities. This has led numerous studies on artificial gaze stabilization, many which are based biological reflexes. stabilization solution includes image capture and processing, inverse kinematics, feedback control achieve desired behavior. Generally, multi-solution problem finding direction kinematics joints solved by using cost functions numerical solvers. results in disadvantages include long processing time, uncertain number iterations, risk instability. In this work, an alternative algebraic method introduced exploiting cascading structure neck eye. By direct equations instead solving, problems utilizing geometrical proposed virtual configurations. Moreover, a sliding mode controller designed move neck-eye their positions. developed scheme simulated MATLAB/SIMULINK environment. Results for various scenarios show can effectively at different stationary moving targets, showing human-like terms timing, quickly achieved stabilized, whereas dynamics stay longer. For simulation cases presented, it took 0.3 seconds more than 1 second.