Drift correction for industrial augmented reality applications

Abstract

In a method for increasing accuracy of augmented reality information presented to a user navigating a real-world mapped environment, a specific object within a field of view of a camera of the user'smobile device is identified, at least by predicting an object type by a machine learning model processing images captured by the camera, and identifying a node that corresponds to the object type within a map database representing the mapped environment. A location associated with the node is retrieved from the map database, and is used to update or confirm one or more estimated locations of the mobile device. Digital information is caused to be superimposed on a real-world view presented to the user via a display of the mobile device, the digital information being selected based at least in part on the updated or confirmed one or more estimated locations of the mobile device.

Description

technical field [0001] In general, this disclosure relates generally to augmented reality technology, and more particularly to augmented reality platforms that may be used in process control or other environments. Background technique [0002] Augmented reality (AR) systems that provide an overlay of digital information (eg, text, images, animations, etc.) in a real-world environment are becoming more common as new applications for the technology are explored. AR systems typically provide information specific to the context of the user's current real-world surroundings. For such systems, real-world knowledge is typically required, such as knowledge of physical things currently in the user's field of view, and the physical layout at and around the user's current location. To make this information available to AR systems, three-dimensional (3D) digital models are typically created that represent the user's environment and the objects within it. The 3D model can then be enhan...

AI Technical Summary

Problems solved by technology

First, in embodiments where such location tracking is used to generate a model of the environment (e.g., a process control environment), any locations fed into the model (e.g., the location of equipment and / or other objects) may be inaccurate

Second, if a user navigating the mapped environment subsequently uses such location tracking, the system may present AR information to the user based on incorrect location information (e.g., by failing to recognize that the user is near a particular object, or by incorrectly determining that the user is near different objects, etc.)

As a result, augmented reality platforms may be substantially less useful (e.g., by limiting the size of factories or other areas where the platform can be effectively used), and / or made more cumbersome (e.g., by requiring a recalibration process in which users periodically location re-registration)

Images