Robot falling protection method and system based on impact prediction and active compliance

Abstract

The invention relates to a robot falling protection method and system based on impact prediction and active compliance. The method comprises the steps of after a robot is subjected to thrust, calculating and obtaining motion control parameters of the robot by using a pre-trained falling protection control model; conducting impact prediction according to the motion control parameters of the robot,and thus obtaining a predicted moment when the robot impacts the ground; and according to the motion control parameters of the robot and the predicted moment when the robot impacts the ground, conducting active compliance on the robot, and thus realizing robot falling protection. The system comprises a falling detection module and a falling protection module. According to the method, the moment when the robot touches the ground is predicted, and active compliance is executed in advance according to the prediction result, so that interference caused by sensor delay is reduced, and impact forceis reduced. The method can be used for falling protection of a humanoid robot, provides help for research and application of the robot in a complex environment, and reduces possible damage to the robot.

Description

technical field [0001] The invention relates to the field of information science, in particular to a robot fall protection method and system based on impact prediction and active compliance. Background technique [0002] The goal of humanoid robot research is to enable robots to go out of the laboratory and have the ability to perform tasks in the environment of human daily work and life. To achieve this goal, the robot needs to be able to handle the inevitable falls. Robot fall control has been researched for more than ten years. During the process, researchers have proposed a series of protective control methods for humanoid robot falls, among which triangular support and active compliance have been proved to be very effective methods. [0003] The triangular support is a humanoid robot forward fall control strategy proposed by referring to the human body protection action in Judo (UKEMI), including rapid squatting to reduce potential energy, bending the knee to touch the...

AI Technical Summary

Problems solved by technology

[0005] In previous work, the active adaptation strategy was often adopted after the impact was detected, which would result in most of the impact energy being absorbed by the robot at the moment of impact on the ground

Taking the active adaptation strategy after the impact moment will reduce the effect of active adaptation

Images