Nonlinear Model Predictive Control of an Aerial Manipulator using a Recurrent Neural Network Model
Nonlinear Model Predictive Control of an Aerial Manipulator using a Recurrent Neural Network Model
复制标题
使用循环神经网络模型对空中机械手进行非线性模型预测控制
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Mathew Sheckells
中科院分区：
文献类型：
--
作者：
Gowtham Garimella;Mathew Sheckells
本工作的目标是通过基于数据驱动的动态模型的模型预测控制来控制由配备有关节式机械臂的无人机（UAV）平台组成的空中机械手系统。学习模型捕获无人机自动驾驶仪的内部闭环动态以及伺服电机控制逻辑。该模型的核心是一个递归神经网络（RNN）架构与前馈模型相结合，以产生施加在机器人上的线加速度和角加速度。然后，以标准方式对这些加速度进行积分，以获得下一个机器人状态。然后，在非线性模型预测控制（NMPC）框架中利用学习的RNN架构，该框架考虑了轨迹优化问题固有的稀疏性。NMPC优化已成功地在DJI Matrice无人机平台上实现，该平台具有定制的双连杆臂以跟踪所需的参考轨迹。
The goal of this work is to control an aerial manipulator system which consists of an Unmanned Aerial Vehicle (UAV) platform equipped with an articulated robotic arm, through model-predictive control based on a data-driven dynamical model. The learned model captures both the internal closed loop dynamics of the UAV autopilot as well as the servo motor control logic. At the core of the model lies a Recurrent Neural Network (RNN) architecture combined with a feedforward model to produce the linear and angular accelerations applied on the robot. These accelerations are then integrated in a standard manner to obtain the next robot state. The learned RNN architecture is then leveraged in a Nonlinear Model Predictive Control (NMPC) framework that accounts for the sparsity inherent to the trajectory optimization problem. The NMPC optimization has been successfully implemented onboard a DJI Matrice UAV platform with a custom made two-link arm to track desired reference trajectories.