物理情報ニューラルネットワークによるロボットのモデリングと制御:理論と実験的検証
Physics-informed Neural Networks to Model and Control Robots: a Theoretical and Experimental Investigation
非保存効果を扱えるよう物理情報ニューラルネットワークを拡張し、モデルベース制御と組み合わせることで、ソフトロボットの運動予測とFranka Emikaマニピュレータの軌道追従を実機で検証した。
著者: Jingyue Liu, Pablo Borja, Cosimo Della Santina
分類: cs.RO
原文アブストラクト
This work concerns the application of physics-informed neural networks to the modeling and control of complex robotic systems. Achieving this goal required extending Physics Informed Neural Networks to handle non-conservative effects. We propose to combine these learned models with model-based controllers originally developed with first-principle models in mind. By combining standard and new techniques, we can achieve precise control performance while proving theoretical stability bounds. These validations include real-world experiments of motion prediction with a soft robot and of trajectory tracking with a Franka Emika manipulator.
