日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

マニピュレーションarXiv:2003.11707

タスク・モーション統合計画とコンプライアント制御によるペグ挿入

Integrating Combined Task and Motion Planning with Compliant Control

シェア:XThreadsFacebookLINEはてブBluesky

双腕ロボットの把持・動作計画をタスク・モーション統合計画で行い、線形探索・螺旋探索・インピーダンス制御を組み合わせたコンプライアント制御でペグ挿入を高精度に実現した。

著者: Hao Chen, Juncheng Li, Weiwei Wan, Zhifeng Huang, Kensuke Harada

分類: cs.RO

原文アブストラクト

Planning a motion for inserting pegs remains an open problem. The difficulty lies in both the inevitable errors in the grasps of a robotic hand and absolute precision problems in robot joint motors. This paper proposes an integral method to solve the problem. The method uses combined task and motion planning to plan the grasps and motion for a dual-arm robot to pick up the objects and move them to assembly poses. Then, it controls the dual-arm robot using a compliant strategy (a combination of linear search, spiral search, and impedance control) to finish up the insertion. The method is implemented on a dual-arm Universal Robots 3 robot. Six objects, including a connector with fifteen peg-in-hole pairs for detailed analysis and other five objects with different contours of pegs and holes for additional validation, were tested by the robot. Experimental results show reasonable force-torque signal changes and end-effector position changes. The proposed method exhibits high robustness and high fidelity in successfully conducting planned peg-in-hole tasks.

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. 2GXO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
  3. 3newmo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
  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