<p>3D reconstruction technology is used in a wide variety of applications. Currently, automatically creating accurate pointclouds for large parts requires expensive hardware. We are interested in using low cost depth camera mounted on commonly available industrial robots for automatically creating accurate pointclouds for large parts. Manufacturing applications require fast cycle times. Therefore, we are interested in speeding up the 3D reconstruction process. We present algorithmic advances in 3D reconstruction that achieve a sub-millimeter accuracy using low-cost depth camera. Our system can be used to determine a pointcloud model of large and complex parts. Advances in camera calibration, cycle time reduction for pointcloud capturing, and uncertainty estimation are made in this work. We present a novel algorithm that finds a robot trajectory using discrete parameter optimization process minimizing the cycle time and maintaining a camera distance from the surface which reduces uncertainty. A pointcloud merging algorithm is presented which continuously captures clouds while robot is executing motion. It maintains a memory efficient data structure to update the output cloud and estimate uncertainty in the measurements. The algorithm enables us to use inexpensive RGB-D sensors like Intel RealSense D415 used in our approach and obtain sub-millimeter measurement accuracy. Our contributions in this paper are, (i) A camera localization method that performs significantly better than existing approaches, (ii) A method to find the robot trajectory that minimizes the cycle time and uncertainty in measurements, and (iii) A method for merging the pointclouds which guarantees a real-time estimation of uncertainty. We provide theoretical basis to show how our method performs to a sub-millimeter accuracy goal that we desire. Our system produces sub millimeter accuracy.</p>

Fast, Accurate, and Automated 3D Reconstruction Using a Depth Camera Mounted on an Industrial Robot

Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2021/volume/85369

ASME 2021 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.