Robotic Machine Vision Solution Can Process Shiny Objects

A solution that enables industrial robots to scan and manipulate metallic objects that are too “shiny” for machine vision to process has been developed by Southwest Research Institute (SwRI) and ROS-Industrial, the industry consortium initiated by SwRI in 2012 to support cost-shared applied R&D for advanced factory automation. The project integrates intelligent part reconstruction using the second generation of the Robot Operating System (ROS2) framework to improve 3D image perception when robots autonomously sand and finish parts.

Machine vision cameras and algorithms have historically struggled to render accurate 3D images of metallic objects due to the “visual noise” that scatters off highly reflective surfaces. This challenge limits automation of welding and surface finishing processes in aerospace and automotive manufacturing.

SwRI and ROS-Industrial integrated intelligent part reconstruction within the ROS2 framework to improve industrial robotics 3D image perception for path planning with way-point dense operations such as parts sanding. Courtesy of Southwest Research Institute.

SwRI, in collaboration with ROS-Industrial, integrated truncated sign distance field algorithms that stitch together several images, or point clouds, at a higher rate. The solution uses trajectory optimization, or TrajOpt, for motion planning, within the ROS-Industrial Scan-N-Plan framework, to enable real-time trajectory planning from 3D scan data. The sensors and robot can be changed out with relatively little effort, said Matt Robinson, an SwRI manager who supports ROS-Industrial.

“This is a great case study in the benefits and challenges of integrating ROS2 into industrial robotics,” Robinson said. “It also shows how advanced perception algorithms can enable faster, more reliable scanning of metallic objects.”

SwRI maintains the ROS-Industrial software repository and manages the ROS-Industrial Consortium. Consortia members in the Americas, Europe, and Asia drive new capabilities in ROS-I by championing focused technical projects based on their near-term automation requirements.

The robotic solution for shiny objects was demonstrated by SwRI at Automate 2019, which took place April 8-11, 2019, at McCormick Place in Chicago.