A Self-Adaptive Online Brain-Machine Interface of a Humanoid Robot Through a General Type-2 Fuzzy Inference System
A Self-Adaptive Online Brain-Machine Interface of a Humanoid Robot Through a General Type-2 Fuzzy Inference System
复制标题
DOI：
10.1109/tfuzz.2016.2637403
复制
发表时间：
2018-02-01
影响因子：
11.9
通讯作者：
Yang, Guang-Zhong
中科院分区：
文献类型：
--
作者：
Andreu-Perez, Javier;Cao, Fan;Yang, Guang-Zhong
本文提出了一种自适应自主在线学习，通过一般的2型模糊系统（GT 2 FS）的运动想象（MI）解码的脑机接口（BMI）和导航的两足人形机器人在真实的实验中，使用脑电图（EEG）的大脑记录。本研究首次将GT 2 FS应用于BMI。我们还考虑了在真实的实践中通常与BMI相关的几个约束：1）EEG通道的最大数量是有限和固定的; 2）不可能执行重复的用户训练会话;以及3）期望使用无监督和低复杂度的特征提取方法。本文提出的新的在线学习方法包括一个自适应GT 2 FS，可以自主自适应其参数和结构，通过创建，融合和缩放的模糊系统规则在一个在线BMI实验与真实的机器人。结构识别是基于在线GT 2 Gath-Geva算法，其中每个MI解码类可以由多个模糊规则（模型）表示，这些规则是在连续（逐个试验）非迭代的基础上学习的。所提出的方法的有效性证明了在一个详细的BMI实验，其中15个未经训练的用户能够准确地与人形机器人接口，在一个单一的会话中，仅使用来自6个EEG电极的信号。
This paper presents a self-adaptive autonomous online learning through a general type-2 fuzzy system (GT2 FS) for the motor imagery (MI) decoding of a brain-machine interface (BMI) and navigation of a bipedal humanoid robot in a real experiment, using electroencephalography (EEG) brain recordings only. GT2 FSs are applied to BMI for the first time in this study. We also account for several constraints commonly associated with BMI in real practice: 1) the maximum number of EEG channels is limited and fixed; 2) no possibility of performing repeated user training sessions; and 3) desirable use of unsupervised and low-complexity feature extraction methods. The novel online learning method presented in this paper consists of a self-adaptive GT2 FS that can autonomously self-adapt both its parameters and structure via creation, fusion, and scaling of the fuzzy system rules in an online BMI experiment with a real robot. The structure identification is based on an online GT2 Gath-Geva algorithm where every MI decoding class can be represented by multiple fuzzy rules (models), which are learnt in a continous (trial-by-trial) non-iterative basis. The effectiveness of the proposed method is demonstrated in a detailed BMI experiment, in which 15 untrained users were able to accurately interface with a humanoid robot, in a single session, using signals from six EEG electrodes only.