日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

外骨格/最適化arXiv:1907.04114

RoboWalk:設計最適化のための人間-ロボット拡張動力学の明示的モデリング

RoboWalk: Explicit Augmented Human-Robot Dynamics Modeling for Design Optimization

シェア:XThreadsFacebookLINEはてブBluesky

下半身支援外骨格RoboWalkについて、人間とロボットの動力学モデルを構築・統合し、PSOによる人間参加型最適化で支援性能を高めつつ人間への負担を減らす設計手法を提案した論文。

著者: S. Ali A. Moosavian, Mahdi Nabipour, Farshid Absalan, Vahid Akbari

分類: cs.RO

原文アブストラクト

Utilizing orthoses and exoskeleton technology in various applications and medical industries, particularly to help elderly and ordinary people in their daily activities is a new growing field for research institutes. In this paper, after introducing an assistive lower limb exoskeleton (RoboWalk), the dynamics models of both multi-body kinematic tree structure human and robot is derived separately, using Newton's method. The obtained models are then verified by comparing the results with those of the Recursive Newton-Euler Algorithms (RNEA). These models are then augmented to investigate the RoboWalk joint torques, and those of the human body, and also the floor reaction force of the complete system. Since RoboWalk is an under-actuated robot, despite the assistive force, an undesirable disturbing force exerts to the human. So, optimization strategies are proposed to find an optimal design to maximize the assistive behavior of RoboWalk and reduce joint torques of the human body as a result. To this end, a human-in-the-loop optimization algorithm will be used. The solution of this optimization problem is carried out by Particle Swarm Optimization (PSO) method. The designed analysis and the optimization results demonstrate the effectiveness of the proposed approaches, leading to the elimination of disturbing forces, lower torque demand for RoboWalk motors and lower weights.

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

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