Model Learning for Robotic Manipulators using Recurrent Neural Networks
Model Learning for Robotic Manipulators using Recurrent Neural Networks
复制标题
DOI：
10.1109/tencon.2019.8929622
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Rajarshi Mukhopadhyay;Ritartha Chaki;A. Sutradhar;P. Chattopadhyay
中科院分区：
文献类型：
--
作者：
Rajarshi Mukhopadhyay;Ritartha Chaki;A. Sutradhar;P. Chattopadhyay
在高自由度和动态、不确定的环境下，传统的机器人分析建模技术的可靠性是有争议的。考虑到这些不确定性和不准确性，研究人员被鼓励使用有监督的机器学习技术作为数据驱动模型学习的更好替代方案。数据驱动模型的主要优势在于其对实时处理模型变化的适应性。考虑到递归神经网络(RNN)家族在序列建模方面的优越性，本文预测这一家族中的三个成员，即简单RNN(SRNN)、长短期记忆(LSTM)和门控递归单元(GRU)有望成为机器人模型学习任务的候选者。使用KUKA LWR和Sarcos Robot ARM 7-DOF的公开数据集进行的仿真结果表明，LSTM和GRU的模型学习性能都优于其他经典的基于回归的方法。
Reliability of the traditional analytical model building techniques for Robotic Manipulators is debatable with higher Degrees of Freedom (DoF) and under dynamic, uncertain environments. Keeping these uncertainties and inaccuracies in the backdrop, the researchers have been encouraged to use supervised machine learning techniques as a better alternative for data-driven model learning. The main advantage of data-driven models lies in their adaptability to cope with the model variations in real-time. Considering the proven superiority of the Recurrent Neural Networks (RNN) family in sequence modelling, this paper projects three members of this family, namely Simple RNN (SRNN), Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) as promising candidates for Robotic manipulator model learning tasks. Simulation results obtained by using some publicly available data sets of KUKA LWR and SARCOS Robot Arm with 7-DoF, clearly show that model learning performance of both LSTM and GRU are better than other classical regression based techniques.