论文标题
具有UUB稳定性的神经网络的自适应模型学习，用于机器人动态估计
Adaptive Model Learning of Neural Networks with UUB Stability for Robot Dynamic Estimation
论文作者
论文摘要
由于批次算法缺乏面对模型不匹配和干扰的熟练程度，因此该贡献提出了一种基于连续Lyapunov功能的自适应方案，用于在线机器人动态识别。本文提出了稳定的更新规则，以驱动从模型参考自适应范式启发的神经网络。网络结构由三个平行的自动驾驶神经网络组成，旨在单独估计机器人动态术语。选择Lyapunov候选者来构建凸优化框架的能量表面。学习规则直接从Lyapunov函数驱动，以使衍生物负面。最后，对3型幻影Omni触觉装置的实验结果证明了该方法的效率。
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.
