Human gesture imitation on NAO humanoid robot using kinect based on inverse kinematics method

Abstract

Humanoid robot is a dynamic robot which can walk with two legs like a human. Many researcher interested in this robot due to its flexibility in reaching a variety of terrain and also its similarity to humans. The main problem often faced by developers is a motion control system which is quite difficult. With 25 DOF, making it difficult to get the desired body posture by controlling it manually. To facilitate the developer, there needs to be a system that can be used as a tool to control robot body movement to get the desired body posture by using human gesture as the input. This system allows us to easily instruct the robot to imitate what we're doing. The system use Kinect as the device to recognize human body and capture information about its skeleton model in 3D. This 3D model will be processed and translated to angle data using inverse kinematics. Then, NAO humanoid robot will get instruction to move based on obtained angle data to perform the imitated body posture.