Humanoid robot gait planning method based on human body teaching

Abstract

The invention discloses a humanoid robot gait planning method based on human body teaching. Human body movement information is used for gait planning of a humanoid robot. The joint driving angle of the robot is obtained through inverse operation of skeleton information during human body movement. The mass center track information of the robot is estimated through human body teaching data in orderto meet the stability during movement of the humanoid robot. Compensation control is conducted on the driving angle of the robot by combining a ZMP criterion and a robot mass center-angle jacobi matrix. In selection of supporting feet, switching of the supporting feet during human body teaching is judged through a hysteretic curve, so that selection of the supporting feet of the robot is determined. The humanoid robot gait planning method based on human body teaching greatly simplifies the complexity of humanoid robot gait planning, and the movement process of the robot is more personified through the gait planning based on human body teaching.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and robot control, in particular to a method for gait planning of a humanoid robot based on human body teaching. Background technique [0002] The structure of the humanoid robot is similar to the human body. In the human social environment, the humanoid robot can replace human beings to complete various tasks, expand human capabilities, and show good environmental adaptability. In recent years, humanoid robots have been widely used in many fields such as service, medical treatment, education, entertainment, etc., and related research work has gradually begun. The research on the walking problem of humanoid robots has always been a major research hotspot in the field of robotics. At present, the main method is to form a stable gait based on the dynamic model combined with the planned ZMP trajectory, but the motion pattern formed by planning often requires complex calculations, and Single fo...

AI Technical Summary

Problems solved by technology

[0004] Although there are many advantages in planning robot gait through human body teaching, since the robot is a direct imitation of the teaching person, this will cause the stability of the robot gait. , it is especially important to control the balance

Different from the open-loop gait planning based on stability criteria, robot gait planning based on human motion faces the following three problems: (1) The human body teaching process provides the driving angle of the robot, but due to the difference in mass distribution, it also needs to be combined with the center of mass The information is compensated and adjusted to meet the balance; (2) the expected ZMP trajectory is no longer set by humans, but is combined with the teaching data to calculate the expected ZMP trajectory; (3) the supporting feet of the human teaching action must be discriminated before use Robot Gait Planning

Images