日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

筋電義手arXiv:2103.02750

筋電義手・腕ロボットシステムのための多チャンネルリアルタイムフィルタリング

Multiple-Channel Real Time Filtering for a Myoelectric Prosthetic Hand-Arm Robot System

シェア:XThreadsFacebookLINEはてブBluesky

データグローブの曲げセンサ信号で制御される義手・腕ロボットに多次元フィルタを追加し、制御信号をリアルタイムで安定化させる手法を開発・実験した。

著者: Weibang Bai, Yinlai Jiang, Hiroshi Yokoi

分類: cs.RO

原文アブストラクト

On the base of the developed master-slave prosthetic hand-arm robot system, which is controlled mainly based on signals obtained from bending sensors fixed on the data glove, the first idea deduced was to develop and add a multi-dimensional filter into the original control system to make the control signals cleaner and more stable at real time. By going further, a second new idea was also proposed to predict new control information based on the combination of a new algorithm and prediction control theory. In order to fulfill the first idea properly, the possible methods to process data in real time, the different ways to produce Gaussian distributed random data, the way to combine the new algorithm with the previous complex program project, and the way to simplify and reduce the running time of the algorithm to maintain the high efficiency, the real time processing with multiple channels of the sensory system and the real-time performance of the control system were researched. Eventually, the experiment on the same provided robot system gives the results of the first idea and shows the improved performance of the filter comparing with the original control method.

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