日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

ソフトロボティクスarXiv:1811.04764

ソフトアクチュエータのための効率的な低次元モデル

Efficient Reduced-Order Models for Soft Actuators

シェア:XThreadsFacebookLINEはてブBluesky

光ファイバひずみセンシングでソフト曲げアクチュエータの変形を高精度に計測し、低次元運動学モデルと3次スプライン補間で連続変形を再構成、リアルタイム運動方程式を導出・検証した。

著者: Yue Chen, Kevin C. Galloway, Isuru S. Godage

分類: cs.RO

原文アブストラクト

Soft robotics have gained increased attention from the robotic community due to their unique features such as compliance and human safety. Impressive amount of soft robotic prototypes have shown their superior performance over their rigid counter parts in healthcare, rehabilitation, and search and rescue applications. However, soft robots are yet to capitalize on their potential outside laboratories and this could be attributed to lack of advanced sensing capabilities and real-time dynamic models. In this pilot study, we explore the use of high-accuracy, high-bandwidth deformation sensing via fiber optic strain sensing (FOSS) in soft bending actuators (SBA). Based on the high density sensor feedback, we introduce a reduced order kinematic model. Together with cubic spline interpolation, this model is able to reconstruct the continuous deformation of SBAs. The kinematic model is extended to derive an efficient real-time equation of motion and validated against the experimental data.

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