Robot tracking method, device and equipment and computer readable storage medium

Abstract

The invention discloses a robot tracking method, device and equipment and a computer readable storage medium, and belongs to the field of intelligent robot control. The method comprises the followingsteps: acquiring observation data of at least two ultrasonic arrays on a robot at each moment of tracking; estimating the motion state of the robot at each moment by utilizing a preset dimension expansion IMM-EKF algorithm, specifically including the following steps: acquiring state estimation corresponding to the robot under each motion model at the moment j through m dimension expansion EKF filters matched with m motion models corresponding to m motion states at the moment k, and acquiring m pieces of state estimation, and performing weighted calculation the m pieces of state estimation to obtain a robot state estimation result at the moment k, wherein each moment is represented by the moment k, and k is an integer larger than 0. According to the invention, the intelligent robot can be stably and effectively tracked under the condition that the motion state of the intelligent robot is unknown and changeable, the false tracking or missing phenomenon is reduced, and the method is suitable for multiple ultrasonic array application scenes.

Description

technical field [0001] The invention relates to the field of intelligent robot control, in particular to a robot tracking method, device, equipment and computer-readable storage medium. Background technique [0002] At present, intelligent robots have been applied in various fields such as marine exploration, security, medical treatment, etc., which have brought great convenience to the development of science and technology and people's lives. Therefore, it is necessary to track robots in real time. However, when the smart robot is working underwater or indoors, satellite positioning cannot be used. The method of visual navigation has the advantages of complete information acquisition and wide detection range, and plays an important role in robot navigation. The disadvantage is that the visual image processing time is long and the real-time performance is poor. Therefore, scholars in the industry have carried out research on mobile robot positioning based on radio frequency...

AI Technical Summary

Problems solved by technology

However, in the actual target tracking process, the motion model is often unknown, and the motion state of the robot often changes, so the tracking effect of the above algorithm will decrease or even diverge.

Images