Deep belief network and linear perceptron based cognitive computing for collaborative robots
Deep belief network and linear perceptron based cognitive computing for collaborative robots
复制标题
用于协作机器人的基于深度信念网络和线性感知器的认知计算
DOI：
10.1016/j.asoc.2020.106300
复制
发表时间：
2020-07-01
影响因子：
8.7
通讯作者：
Qiao, Liang
中科院分区：
文献类型：
--
作者：
Lv, Zhihan;Qiao, Liang
目的：分析基于认知计算技术的协作机器人控制系统的性能。研究方法：将认知计算和深度信念网络算法与协作机器人相结合，构建了基于深度信念网络的认知计算系统模型，并将其应用于协作机器人的控制系统中。进一步，通过仿真比较分析了深度信念网络（DBN）、多层感知器（MLP）以及本文提出的深度信念网络和线性感知器（DBNLP）的认知计算系统模型的算法性能。结果如下：结果表明，与DBN和MLP算法相比，DBNLP算法模型在训练集重复次数、隐层神经元个数和网络层数上具有明显更低的错误率。并且任务积压数、待分配资源数和时间消耗都较少，以及准确率高。通过比较分析Ex（期望值）、En（熵值）和He（超熵值）估计值的变化，发现DBNLP算法模型的估计值比DBN和MLP算法更接近真实值。结论：将DBNLP算法模型应用于协作机器人，可以显著提高其准确性和安全性，为后期协作机器人的性能提升提供实验基础。(C)2020爱思唯尔B.V.保留所有权利。
Objective: This paper is to analyze the performance of the control system of collaborative robots based on cognitive computing technology. Methods: This study combines cognitive computing and deep belief network algorithms with collaborative robots to construct a cognitive computing system model based on deep belief networks, which is applied to the control system of collaborative robots. Further, the simulation is used to compare and analyze the algorithm performance of deep belief network (DBN), multilayer perceptron (MLP) and the cognitive computing system model of deep belief network and linear perceptron (DBNLP) proposed in this study. Results: The results show that compared with the DBN and MLP algorithms, the DBNLP algorithm model has a significantly lower error rate in the number of repetitions of the training set, the number of hidden neurons, and the number of network layers. And the number of task backlog, the number of resources to be allocated and the time consumption are less, as well as the accuracy is high. After comparing and analyzing the changes in the estimated value of Ex (expected value), En (entropy value) and He (hyper entropy value), it is found that the estimated value of the DBNLP algorithm model is closer to the true value than that of the DBN and MLP algorithms. Conclusion: The application of the DBNLP algorithm model to collaborative robots can significantly improve its accuracy and safety, providing an experimental basis for the performance improvement of later collaborative robots. (C) 2020 Elsevier B.V. All rights reserved.