Gait parameters optimization and real-time trajectory planning for humanoid robots

Trajectory planning of humanoid robots not only is required to satisfy kinematic constraints, but also other criteria such as staying balance, having desirable upper and lower postures, having smooth movement etc, is needed to maintain certain properties. In this paper, calculation formulas of driving torque for each joint of humanoid robot are derived based on dynamics equation, mathematic models for gait parameters optimization are established via introducing energy consumption indexes. gait parameters are optimized utilizing genetic algorithm. A new approach for real-time trajectory planning of humanoid robots is proposed based on fuzzy neural network (FNN), Zero Moment Point (ZMP) criteria, B-spline interpolation and inverse displacement analysis model. The minimum energy consumption gait, which similar with human motion, are used to train FNN, b-spline curves are utilized to fit dispersive Center of Gravity (COG) position and body posture datas, based on above models and inverse displacement model, trajectory of COG and desired body posture can be mapped into trajectory of joint space conveniently. Simulation results demonstrate feasibility and effectiveness of above real-time trajectory planning method. Numeric examples are given for illustration.