Skip navigation

Seminar: Scene Understanding for Adaptive Manipulation in Robotized Construction Work

Event Date: December 8, 2017
Speaker: Vineet Kamat, PhD
Speaker Affiliation: University of Michigan
Time: 1:30 - 2:20 pm
Location: HAMP 2123
Contact Name: Kyu Kang
Contact Email: kang156@purdue.edu
Priority: No
School or Program: Construction Engineering and Management
College Calendar: Show
Vineet Kamat — Professor and John L. Tishman Faculty Scholar in the Department of Civil and Environmental Engineering at University of Michigan—will speak at 1:30pm Dec. 8 in Hampton Hall Room 2123.

Seminar: Scene Understanding for Adaptive Manipulation in Robotized Construction Work

Vineet Kamat, PhD
Professor, Department of Civil and Environmental Engineering
John L. Tishman Faculty Scholar
University of Michigan

December 8, 2017
1:30 PM
HAMP 2123

For more information:  Kyu Kang, kang156@purdue.edu


Abstract

Unlike manufacturing robots, whose kinematics are pre-programmed based on robust metrology, tight tolerances, and rigid work pieces, construction robots operate under conditions of imperfect metrology, loose tolerances, and large work piece uncertainties. Despite having access to a designed Building Information Model (BIM), construction robots must sense and model their actual environment, and adapt their kinematic plan to compensate for deviations from the expected.

This talk will present methods to enable the autonomous sensing and modeling of construction objects so construction robots can ultimately adapt to unexpected circumstances and perform quality work. To that end, two construction component model fitting techniques are introduced, namely the Clustering and Iterative Closest Point (CICP) construction component model fitting technique and the Generalized Resolution Correlative Scan Matching (GRCSM) construction component model fitting technique. The GRCSM construction component model-fitting technique employs the presented GRCSM search algorithm, which is a modified version of the existing Multi-Resolution Correlative Scan Matching (MRCSM) algorithm. Three experiments are presented to evaluate the ability of the CICP and GRCSM construction component model fitting techniques to model construction features.

It was found that the CICP and GRCSM construction component model fitting techniques are capable of estimating the pose and geometry of arbitrarily shaped objects and construction joints, but are susceptible to modeling failure under some conditions. Despite their limitations, the CICP and GRCSM construction component model fitting techniques appear to be promising tools for the geometric estimation of construction features, especially for situations involving full automation, detailed construction work, incomplete sensor data, and complex object geometry.


Dr. Vineet R. Kamat is a Professor and the John L. Tishman Faculty Scholar in the Department of Civil and Environmental Engineering at the University of Michigan. He directs the Laboratory for Interactive Visualization in Engineering and co-directs the Construction Engineering Laboratory. Dr. Kamat’s research is primarily focused on Virtual and Augmented Reality Visualization, Simulation, Mobile Computing, Robotics, and their applications in Construction. Dr. Kamat was awarded the 2015 Walter L. Huber Civil Engineering Research Prize by the American Society of Civil Engineers. He has also received the Daniel W. Halpin Award for scholarship in construction from the American Society of Civil Engineers; the Outstanding Early Career Researcher Award from FIATECH; and two Outstanding Young Alumnus Awards from the Department of Civil and Environmental Engineering, and the Myers-Lawson School of Construction at Virginia Tech. He has also received three ASCE Best Paper Awards, from the Journal of Computing in Civil Engineering, and the Construction Research Congress. He received a NSF CAREER Award in 2005. Dr. Kamat is an Associate Editor of the ASCE Journal of Computing in Civil Engineering and a member of the editorial board for the journal Automation in Construction and the journal Advanced Engineering Informatics. He has served as the Chair of the ASCE Construction Institute’s Construction Research Council, and as a Member of the Board of Governors of the ASCE Construction Institute. He has also served as the Chair of the ASCE Visualization, Information Modeling and Simulation committee. Dr. Kamat’s research has been published in 55 peer-reviewed journal publications and 65 conference papers to date. He has presented his work in 32 invited talks throughout the world and has organized several technical sessions on construction visualization at all major conferences in his field of research. Dr. Kamat received a Ph.D. in Civil Engineering at Virginia Polytechnic Institute and State University in 2003; a MS in Civil Engineering at Virginia Polytechnic Institute and State University in 2000; and a BE degree in Civil Engineering from Goa University in India in 1998.