再考された遅延確率的ロードマップ
Lazy Probabilistic Roadmaps Revisited
PRMと新しい分枝カット法を組み合わせ、動的に制約を生成して滑らかな経路計画を効率的に探索する手法を提案し、ベンチマークで評価した。
著者: Miquel Ramirez, Daniel Selvaratnam, Chris Manzie
分類: cs.RO, cs.AI
原文アブストラクト
This paper describes a revision of the classic Lazy Probabilistic Roadmaps algorithm (Lazy PRM), that results from pairing PRM and a novel Branch-and-Cut (BC) algorithm. Cuts are dynamically generated constraints that are imposed on minimum cost paths over the geometric graphs selected by PRM. Cuts eliminate paths that cannot be mapped into smooth plans that satisfy suitably defined kinematic constraints. We generate candidate smooth plans by fitting splines to vertices in minimum-cost path. Plans are validated with a recently proposed algorithm that maps them into finite traces, without need to choose a fixed discretization step. Trace elements exactly describe when plans cross constraint boundaries modulo arithmetic precision. We evaluate several planners using our methods over the recently proposed BARN benchmark, and we report evidence of the scalability of our approach.
