日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

歩行arXiv:2005.00347

スラスタ支援二足歩行の効率とロバスト性向上に向けて

Towards thruster-assisted bipedal locomotion for enhanced efficiency and robustness

シェア:XThreadsFacebookLINEはてブBluesky

二足歩行ロボットにスラスタを併用し、参照ガバナと予測制御で関節軌道を微調整することで、単脚支持期の性能制約を満たしつつハイブリッド不変性をロバストに保つ制御手法を提案した。

著者: Pravin Dangol, Alireza Ramezani

分類: cs.RO, cs.SY, eess.SY

原文アブストラクト

In this paper, we will report our efforts in designing closed-loop feedback for the thruster-assisted walking of bipedal robots. We will assume for well-tuned supervisory controllers and will focus on fine-tuning the joints desired trajectories to satisfy the performance being sought. In doing this, we will devise an intermediary filter based on reference governors that guarantees the satisfaction of performance-related constraints. Since these modifications and impact events lead to deviations from the desired periodic orbits, we will guarantee hybrid invariance in a robust way by applying predictive schemes withing a very short time envelope during the gait cycle. To achieve the hybrid invariance, we will leverage the unique features in our model, that is, the thrusters. The merit of our approach is that unlike existing optimization-based nonlinear control methods, satisfying performance-related constraints during the single support phase does not rely on expensive numeric approaches. In addition, the overall structure of the proposed thruster-assisted gait control allows for exploiting performance and robustness enhancing capabilities during specific parts of the gait cycle, which is unusual and not reported before.

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. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXO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
  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