In the continuous development process, robot technology has been widely used in aerospace, medical, education and service industries, and the relationship between robots and humans is getting closer.The improvement of robot intelligence is a process of continuously learning outside knowledge.Since the introduction of human-computer interaction technology in 1959, it has provided more and more technical support for human research robots.This paper first takes Taijiquan as an example, and carries out mechanical analysis and deconstruction of its standard Taiji pusher action, and obtains corresponding action parameterization information;Then, based on the human-computer interaction technology, the human body depth image and the skeleton structure are acquired through the Kinect sensor, and the human joint position data is recorded.The coordinate conversion is sent to the Nao robot, which realizes the imitation learning of the robot's push action on the Taiji.
© Copyright 2020 EURASIP Journal on Wireless Communications and Networking. Springer. Alle Rechte vorbehalten.