地図なし局所ナビゲーションのためのGPフロンティア
GP-Frontier for Local Mapless Navigation
スパースガウス過程の不確かさ評価に基づくGPフロンティアを提案し、地図や経路計画なしに局所的な測距センサのみで安全かつ持続的にロボットを目標へ誘導できることを示した。
著者: Mahmoud Ali, Lantao Liu
分類: cs.RO
原文アブストラクト
We propose a new frontier concept called the Gaussian Process Frontier (GP-Frontier) that can be used to locally navigate a robot towards a goal without building a map. The GP-Frontier is built on the uncertainty assessment of an efficient variant of sparse Gaussian Process. Based only on local ranging sensing measurement, the GP-Frontier can be used for navigation in both known and unknown environments. The proposed method is validated through intensive evaluations, and the results show that the GP-Frontier can navigate the robot in a safe and persistent way, i.e., the robot moves in the most open space (thus reducing the risk of collision) without relying on a map or a path planner.
