Bionic vision self-motion perception map drawing method, storage medium and equipment

Abstract

The invention discloses a bionic vision self-motion perception map drawing method, a storage medium and equipment. The method comprises steps of building a scene memory unit representing a spatial position and an environment landmark template according to the environment information collected by a bionic vision perception system, and generating a corresponding scene memory database; acquiring self-motion information according to a gyroscope and an accelerometer, performing direction and displacement encoding, and updating pose sensing information; correcting the self-motion information by adopting a scene memory bank and an environment landmark template; and drawing and correcting the bionic self-motion perception map according to the mutual relation among the environmental landmark template, the scene memory unit and the self-motion perception. The method is advantaged in that self-motion sensing errors can be reduced by using the visual sensing template, and precision of self-positioning and accuracy of closed-loop detection of the scene memory unit are improved.

Description

technical field [0001] The invention belongs to the technical field of SALM (instant positioning and map construction technology), and relates to a bionic visual self-motion perception map drawing method, a storage medium and a device. Background technique [0002] The core problem of SALM technology (instant positioning and map construction technology) is that the robot is required to first explore the environment in an unfamiliar environment to understand the environment (build a map), and simultaneously use the map to track the position of the robot in the environment (positioning) . The traditional solution to the SALM problem is mainly based on mathematical probability methods, among which Kalman filter, particle filter and maximum expectation algorithm are the basic solutions to the robot SALM problem. Although these traditional SALM algorithms still use laser ranging and sonar ranging to collect information, the information collected by these sensors is often inaccur...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a trajectory control method for automatic driving to solve the problems in the prior art that the position coordinates cannot be updated in real time, the image matching accuracy and positioning accuracy are poor, and the two-dimensional position estimation map is seriously distorted.

Images