Robot Learning System Based on Adaptive Neural Control and Dynamic Movement Primitives
Robot Learning System Based on Adaptive Neural Control and Dynamic Movement Primitives
复制标题
基于自适应神经控制和动态运动原语的机器人学习系统
DOI：
10.1109/tnnls.2018.2852711
复制
发表时间：
2019-03-01
影响因子：
10.4
通讯作者：
Li, Zhijun
中科院分区：
文献类型：
--
作者：
Yang, Chenguang;Chen, Chuize;Li, Zhijun
提出了一种同时考虑运动生成和轨迹跟踪的增强机器人技能学习系统。在机器人学习演示中，动态运动原语（dmp）被用于机器人运动建模。每个DMP由一组动态系统组成，这些系统增强了生成的运动朝着目标的稳定性。将高斯混合模型和高斯混合回归相结合，提高了DMP的学习性能，从而可以从多个演示中提取更多的技能特征。由学习到的模型产生的运动可以在空间和时间上缩放。此外，设计了基于神经网络的控制器，对运动模型生成的轨迹进行跟踪。在该控制器中，采用径向基函数神经网络对动态环境的影响进行补偿。使用Baxter机器人进行了实验，结果证实了所提出方法的有效性。
This paper proposes an enhanced robot skill learning system considering both motion generation and trajectory tracking. During robot learning demonstrations, dynamic movement primitives (DMPs) are used to model robotic motion. Each DMP consists of a set of dynamic systems that enhances the stability of the generated motion toward the goal. A Gaussian mixture model and Gaussian mixture regression are integrated to improve the learning performance of the DMP, such that more features of the skill can be extracted from multiple demonstrations. The motion generated from the learned model can be scaled in space and time. Besides, a neural-network-based controller is designed for the robot to track the trajectories generated from the motion model. In this controller, a radial basis function neural network is used to compensate for the effect caused by the dynamic environments. The experiments have been performed using a Baxter robot and the results have confirmed the validity of the proposed methods.