UUB安定性を保証するニューラルネットワークの適応モデル学習によるロボット動特性推定
Adaptive Model Learning of Neural Networks with UUB Stability for Robot Dynamic Estimation
リアルタイムのロボット動特性同定のために、Lyapunov関数に基づく安定な適応学習則を提案し、3自由度ハプティックデバイスで有効性を実証した。
著者: Pedram Agand, Mahdi Aliyari Shoorehdeli
分類: cs.RO, cs.NE, cs.SY, eess.SY
原文アブストラクト
Since batch algorithms suffer from lack of proficiency in confronting model mismatches and disturbances, this contribution proposes an adaptive scheme based on continuous Lyapunov function for online robot dynamic identification. This paper suggests stable updating rules to drive neural networks inspiring from model reference adaptive paradigm. Network structure consists of three parallel self-driving neural networks which aim to estimate robot dynamic terms individually. Lyapunov candidate is selected to construct energy surface for a convex optimization framework. Learning rules are driven directly from Lyapunov functions to make the derivative negative. Finally, experimental results on 3-DOF Phantom Omni Haptic device demonstrate efficiency of the proposed method.
