日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

探索arXiv:2004.08535

ハイブリッド地図表現を用いた複雑未知環境の自己探査

Self-Exploration in Complex Unknown Environments using Hybrid Map Representation

シェア:XThreadsFacebookLINEはてブBluesky

GVDベースのトポロジカル地図とグリッド地図を組み合わせたハイブリッド表現を提案し、グローバル・ローカルな階層的フロンティア探索で複雑環境の探査効率を向上させた。

著者: Wenchao Gao, Matthew Booker, Jiadong Wang

分類: cs.RO

原文アブストラクト

A hybrid map representation, which consists of a modified generalized Voronoi Diagram (GVD)-based topological map and a grid-based metric map, is proposed to facilitate a new frontier-driven exploration strategy. Exploration frontiers are the regions on the boundary between open space and unexplored space. A mobile robot is able to construct its map by adding new space and moving to unvisited frontiers until the entire environment has been explored. The existing exploration methods suffer from low exploration efficiency in complex environments due to the lack of a systematical way to determine and assign optimal exploration command. Leveraging on the abstracted information from the GVD map (global) and the detected frontier in the local sliding window, a global-local exploration strategy is proposed to handle the exploration task in a hierarchical manner. The new exploration algorithm is able to create a modified tree structure to represent the environment while consolidating global frontier information during the self-exploration. The proposed method is verified in simulated environments, and then tested in real-world office environments as well.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  5. 5Google DeepMind、ロボット向けAIを発表新製品・発表

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI