Sampling-based coverage path planning for inspection of complex structures

Brendan Englot, Franz S. Hover

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

102 Scopus citations

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.

Original languageEnglish
Title of host publicationICAPS 2012 - Proceedings of the 22nd International Conference on Automated Planning and Scheduling
Pages29-37
Number of pages9
StatePublished - 2012
Event22nd International Conference on Automated Planning and Scheduling, ICAPS 2012 - Atibaia, Sao Paulo, Brazil
Duration: 25 Jun 201229 Jun 2012

Publication series

NameICAPS 2012 - Proceedings of the 22nd International Conference on Automated Planning and Scheduling

Conference

Conference22nd International Conference on Automated Planning and Scheduling, ICAPS 2012
Country/TerritoryBrazil
CityAtibaia, Sao Paulo
Period25/06/1229/06/12

Fingerprint

Dive into the research topics of 'Sampling-based coverage path planning for inspection of complex structures'. Together they form a unique fingerprint.

Cite this