WIRELESS KINECT-NAO FRAMEWORK BASED ON TAKAGI-SUGENO FUZZY INFERENCE SYSTEM

What is it about?

In the context of learning new skills by imitation for children with special educational needs, we propose Wireless Kinect-NAO Framework (WKNF) for robot teleoperation based on Takagi-Sugeno (T-S) Fuzzy Inference System. The innovative solutions here are related to view invariant teleoperation, work online, smoothness in motion retargeting by median filter and fuzzifying of depth Kinect data, motion mapping of Human to NAO movements by featured angles rather than direct Inverse Kinematics angles. The nonlinearity of the observed 3D Kinect angles in different offsets is linearly approximated by T-S fuzzy rules of zero and first order that have local support in 2D projections. The feasibility of framework has been proven by real experiments.

Featured Image