US2017297198A1PendingUtilityA1

Supervised Autonomous Robotic System for Complex Surface Inspection and Processing

Assignee: UNIV CARNEGIE MELLONPriority: Mar 15, 2013Filed: Apr 25, 2017Published: Oct 19, 2017
Est. expiryMar 15, 2033(~6.6 yrs left)· nominal 20-yr term from priority
G01N 21/9515Y10S901/28G01B 11/24B25J 9/1664B25J 9/1697Y10S901/41Y10S901/47Y10S901/44G05B 19/4099B25J 9/1671G05B 2219/45071Y10S901/06G05B 2219/37449B23Q 17/2233
54
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

The invention disclosed herein describes a supervised autonomy system designed to precisely model, inspect and process the surfaces of complex three-dimensional objects. The current application context for this system is laser coating removal of aircraft, but this invention is suitable for use in a wide variety of applications that require close, precise positioning and maneuvering of an inspection or processing tool over the entire surface of a physical object. For example, this system, in addition to laser coating removal, could also apply new coatings, perform fine-grained or gross inspection tasks, deliver and/or use manufacturing process tools or instruments, and/or verify the results of other manufacturing processes such as but not limited to welding, riveting, or the placement of various surface markings or fixtures.

Claims

exact text as granted — not AI-modified
We claim: 
     
         1 . A system for processing the surface of an aircraft, comprising:
 a mobile base unit;   an industrial manipulator, attached to said mobile base unit;   an end effector, attached to said industrial manipulator;   one or more machine vision components, attached to said end effector; and   a surface processing device, attached to said end effector.   
     
     
         2 . The system of  claim 1  wherein said vision components gather data about the surface of an aircraft relative to said surface processing device; 
     
     
         3 . The system of  claim 2  wherein said data includes color, texture and abstract classification results. 
     
     
         4 . The system of  claim 3  wherein said data further includes estimates of the distance and orientation of the surface relative to said surface processing device. 
     
     
         5 . The system of  claim 4  wherein said data is stored in a surface model. 
     
     
         6 . The system of  claim 4  wherein said machine vision components comprise:
 one or more multi-spectral cameras; and 
 illumination sources corresponding to said cameras; 
 wherein said machine vision components can discriminate between various layers of paint and the underlying substrate on the surface of the aircraft. 
 
     
     
         7 . The system of  claim 6  wherein said surface processing device is a high-power laser scanner. 
     
     
         8 . The system of  claim 6  wherein said machine vision components estimate the present state of the surface to determine if further processing by said surface processing device is required. 
     
     
         9 . The system of  claim 5  where said system further comprises a computer for controlling said system and software running on said computer said software performing the functions of:
 classifying all areas of the surface of the aircraft based on data collected by said machine vision components and updating said surface model with said results; 
 planning a sequence of processing actions for said surface processing device, based on said surface model; 
 collecting real-time feedback as to the state of the surface as said surface processing device processes the surface; and 
 modulating the operating characteristics of the surface processing device based on said real-time feedback. 
 
     
     
         10 . The system of  claim 9  wherein said software performs the further function of planning movements of said system to ensure processing coverage of the entire surface of said aircraft.

Join the waitlist — get patent alerts

Track US2017297198A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.