Free floating target capturing method based on 3D vision and imitation learning

Abstract

The invention discloses a free floating target capturing method based on 3D vision and imitation learning. The method mainly comprises the following three parts: firstly, acquiring the position and posture of a target capture point in real time by using a depth camera; secondly, estimating a motion state by using Kalman filtering according to historical data, and predicting a track of free floating in a future period of time according to motion information; and finally, determining the capture opportunity and the pose of the capture point at the moment, collecting capture data of the person, establishing a skill model, and migrating the skill model to the robot for capture. Pose estimation, trajectory prediction and mechanical arm trajectory planning technologies in the process are completed on the basis of vision and imitation learning, autonomous capture of a free floating target is achieved, and capture requirements can be well met.

Description

technical field [0001] The invention relates to the field of space robots, in particular to a free-floating target capture method based on 3D vision and imitation learning. Background technique [0002] The pace of human development and utilization of outer space is constantly accelerating. The world launches 80 to 130 satellites every year, and about 10% of them fail due to failures. These debris occupy precious orbital resources; Its main components can still work normally when the scheduled missions and fuel are exhausted, which constitutes a serious safety hazard for other spacecraft in orbit; the use of space robots to complete tasks such as orbital debris cleaning, on-orbit maintenance, maintenance and upgrades, and space station assembly has a great impact on improving Utilization of space orbits, reducing costs, recovering economic losses, prolonging the life of spacecraft, improving the on-orbit performance of spacecraft, and improving economic benefits play an imp...

AI Technical Summary

Problems solved by technology

[0003] At present, most of the on-orbit robots are captured by teleoperation or astronauts on-orbit auxiliary robots, which have low autonomy, and the time delay of the control signal will also bring instability, resulting in poor accuracy and high cost.

[0004] Autonomous space robots integrate multiple sensors such as vision and force, and can replace astronauts or ground operators to control and capture operations. Therefore, all aerospace powers are conducting research and demonstrations on the key technologies of space robots on-orbit capture, but currently Most of the research results are in the conceptual design stage, and there is still a big gap from the actual application

Images