An Indoor Robot Localization Method Fusion of Visual Odometry and Physical Odometry

Abstract

The invention discloses an indoor robot positioning method by combining a visual odometer and a physical odometer. The method is characterized in that by collecting the images, ORB characteristics are extracted for image coupling, camera position and pose estimation, and closed loop detection to accurately position the robot. The visual odometer is added in a known environment for closed loop detection on the robot, the accumulated error of the physical odometer based on particle filter is eliminated, the global error of the odometer is changed to staggered accumulation, and an closed is established based on the above process. The visual odometer is combined for effectively solving the problem of error accumulation of the physical odometer, and realizes automatic positioning and accurate re-positioning of the robot in the known environment, the increased computation burden is not large, efficiency and real-time performance are guaranteed, indoor navigation requirement can be preciously satisfied, and the indoor robot positioning method is effective for solving the problem of inaccurate positioning of the robot under large environment in the prior art.

Description

technical field [0001] The invention relates to a method for autonomous positioning accuracy of an indoor mobile robot, in particular to an indoor robot positioning method that combines visual odometers and physical odometers. Background technique [0002] In the related research on intelligent navigation technology of autonomous mobile robots, the simultaneous localization and mapping (SLAM) technology of robots in unknown environments is a key technology, which has both engineering and academic values. research hotspots in the field. Under this trend, scholars have proposed a variety of methods to solve the SLAM problem, and also applied a variety of sensors to solve the environmental perception problem in SLAM. [0003] The first problem to be solved by SLAM technology is to select an appropriate sensor system to realize the real-time positioning of the robot. In practical applications, sensors based on laser radar with high accuracy in ranging range and azimuth are the...

AI Technical Summary

Problems solved by technology

[0004] The existing technology can satisfy the robot in an indoor environment with a simple structure and a small area through the improved Monte Carlo particle filter and the positioning method of the physical odometer. However, the physical odometer is calculated by the displacement increment of two time periods. , it only considers local motion, so the error will continue to accumulate until the drift is too large to be eliminated, especially when the wheel slips or tilts, the positioning error will be greater

Images