Simultaneous localization and mapping method and device based on rodent model

Abstract

The invention provides a simultaneous localization and mapping method and device based on a rodent model. The method comprises the following steps: acquiring a current visual image of a robot transmitted by a pick-up device; acquiring the displacement speed, the angular velocity of rotation and the direction of a characteristic region of the current vision image, transmitted by a visual odometer;performing network activity updating on the pose cellular network according to the displacement speed, the rotating angular velocity and the direction; calculating the maximal scene similarity of thecurrent vision image and a vision image information base, and acquiring the corresponding first pose coordination of a template image with the maximal scene similarity; updating the vision image information base according to the maximal scene similarity; and determining the current experience point according to the activity degree of the pose cellular network, the current vision image informationbase, the first pose coordination and a preset experience map so as to realize localization and correction on the robot and draw an actual experience chart to perform the simultaneous localization andmapping on the robot.

Description

[0001] technology neighborhood [0002] The invention relates to a robot control neighborhood, in particular to a method and device for synchronous positioning and map construction based on a rodent model. Background technique [0003] Simultaneous localization and map construction are major challenges for mobile robots. Because the mobile robot is essentially a mobile sensor platform, although the types and capabilities of the sensors are different, there are widespread problems such as odometry drift and different noises. Later, after continuous exploration by scholars, bionic robots (robots controlled by bionic technology) gradually showed good application prospects, showing perfect biological rationality and high adaptability to the natural environment. Among them, most bionic robots use rodent animal models for bionic technology. [0004] Among them, the rodent model integrates visual odometer information and visual scene image information into the pose perception cell ...

AI Technical Summary

Problems solved by technology

At present, rodent models have been widely used in the positioning and navigation of robots, solving many problems that are difficult to solve in Simultaneous Localization and Mapping (SLAM), but the visual scene image information obtained by rodent models and There is a certain degree of error in the visual odometry information. Although some scholars have introduced FAB-MAP (fast appearance based mapping) for the error of the visual odometer, this closed-loop detection algorithm based on the historical model can improve the system by matching key frames in real time. stability, but the positioning accuracy is not stable, and the robustness is not strong

Therefore, a separate rodent model needs to be further improved in terms of positioning accuracy and robustness

Images