A Topology-Based Path Similarity Metric and its Application to Sampling-Based Motion Planning
العنوان: | A Topology-Based Path Similarity Metric and its Application to Sampling-Based Motion Planning |
---|---|
المؤلفون: | Hanglin Zhou, Jory Denny, Kaiwen Chen |
المصدر: | IROS |
بيانات النشر: | IEEE, 2018. |
سنة النشر: | 2018 |
مصطلحات موضوعية: | 0209 industrial biotechnology, Computer science, Homotopy, Robot manipulator, 010103 numerical & computational mathematics, 02 engineering and technology, Workspace, 01 natural sciences, Computer Science::Robotics, 020901 industrial engineering & automation, Motion planning, 0101 mathematics, Equivalence (formal languages), Algorithm |
الوصف: | Many applications of robotic motion planning benefit from considering multiple homotopically distinct paths rather than a single path from start to goal. However, determining whether paths represent different homotopy classes can be difficult to compute. We propose metrics for efficiently approximating the homotopic similarity of two paths are, instead of verifying homotopy equivalence directly. We propose two metrics: (1) a naive application of local planning, a common subroutine of sampling-based motion planning, and (2) a novel approach that reasons about the topologically distinct portions of the workspace that a path visits. We present three applications of our metric to demonstrate its use and effectiveness: extracting topologically distinct paths from an existing roadmap, comparing paths for robot manipulators, and improving the computational efficiency of an existing sampling-based method, Path Deformation Roadmaps (PDRs), by over two orders of magnitude. We explore the trade-off between quality and computational efficiency in the proposed metrics. |
DOI: | 10.1109/iros.2018.8594325 |
URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::56dbd61bf252a3e0a091bdba523b75be https://doi.org/10.1109/iros.2018.8594325 |
رقم الانضمام: | edsair.doi...........56dbd61bf252a3e0a091bdba523b75be |
قاعدة البيانات: | OpenAIRE |
كن أول من يترك تعليقا!