Succicnt Accurate and Real Time Map Compression by Mobile Robots

2014 Fiscal Year Final Research Report

• Project/Area Number: 23700229
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: University of Fukui
• Principal Investigator: TANAKA Kanji 福井大学, 工学(系)研究科(研究院), 准教授 (30325899)
• Project Period (FY): 2011-04-28 – 2015-03-31
• Keywords: SLAM技術 / ロボットビジョン / 共通物体発見 / 地図生成 / 移動ロボット / 自己位置推定 / 自律移動ロボット / 辞書式圧縮

Outline of Final Research Achievements

We realized map compression techniques towards robotic large scale map building applications. Our method enables a robot to obtain a compact representation of an environment map while simultaneously building the map. To this end, we proposed and developed methods for data compression exploiting repetitive patterns in the map, efficient algorithm for detecting repetitive patterns, efficient representation of the map, and experimentally verified the effectiveness of the proposed method.

Free Research Field

ロボット工学