Sampling-Based Coverage Path Planning for Inspection of Complex Structures
Name
Brendan Englot ICAPS final version submitted March 2012.pdf
Size
1.86 MB
Format
Adobe PDF
Checksum (MD5)
ddde34fa3202e49568be52037fe250a7
Author(s)
Englot, Brendan J.
Hover, Franz S.
Date Issued
June 2012
Journal
Proceedings of the 2012 International Conference on Automated Planning and Scheduling, ICAPS 2012
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Citation
Englot, Brendan and Franz S. Hover. "Sampling-Based Coverage Path Planning for Inspection of Complex Structures." ICAPS 2012, 22nd International Conference on Automated Planning and Scheduling, Atibaia, Sao Paulo Brazil, June 25-29, 2012.
Version
Author's final manuscript
Abstract
We present several new contributions in sampling-based coverage path planning, the task of finding feasible paths that give 100% sensor coverage of complex structures in obstacle-filled and visually occluded environments. First, we establish a framework for analyzing the probabilistic completeness of a sampling-based coverage algorithm, and derive results on the completeness and convergence of existing algorithms. Second, we introduce a new algorithm for the iterative improvement of a feasible coverage path; this relies on a sampling-based subroutine that makes asymptotically optimal local improvements to a feasible coverage path based on a strong generalization of the RRT algorithm. We then apply the algorithm to the real-world task of autonomous in-water ship hull inspection. We use our improvement algorithm in conjunction with redundant roadmap coverage planning algorithm to produce paths that cover complex 3D environments with unprecedented efficiency.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://www.aaai.org/ocs/index.php/ICAPS/ICAPS12/paper/view/4728/4711
