日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

経路計画arXiv:1410.4145

ライントレースロボットの迷路解法アルゴリズムと非線形経路からの直線距離導出

Maze solving Algorithm for line following robot and derivation of linear path distance from nonlinear path

シェア:XThreadsFacebookLINEはてブBluesky

ライントレースロボットが任意のラインメイズを探索・解決する汎用アルゴリズムを提案し、迷路を座標系でグラフ化してダイクストラ法で最短経路を求める。さらに非線形移動時のエンコーダ誤差を補正し直線距離を導出する式を構築した。

著者: Shadman Sakib, Anik Chowdhury, Shekh Tanvir Ahamed, Syed Imam Hasan

分類: cs.RO

原文アブストラクト

In this paper we have discussed a unique general algorithm for exploring and solving any kind of line maze with another simple one for simple mazes without loops or loops having highest two branches none of which are inward. For the general algorithm, we need a method to map the whole maze, which is required if the maze is complex. The proposed maze mapping system is based on coordinate system and after mapping the whole maze as a graph in standard 'Adjacency-list representation' method, shortest path and shortest time path was extracted using Dijkstra's algorithm. In order to find the coordinates of the turning points and junctions, linear distance between the points are needed, for which wheel encoder was used. However, due to non-linear movement of robot, the directly measured distance from the encoder has some error and to remove this error an idea is built up which ended by deriving equations that gives us almost exact linear distance between two points from the reading of wheel encoder of the robot moving in a non-linear path.

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. 3GXO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
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI