KNODE-MPC: A Knowledge-Based Data-Driven Predictive Control Framework for Aerial Robots
KNODE-MPC: A Knowledge-Based Data-Driven Predictive Control Framework for Aerial Robots
复制标题
DOI：
10.1109/lra.2022.3144787
复制
发表时间：
2022-04-01
影响因子：
5.2
通讯作者：
Hsieh, M. Ani
中科院分区：
文献类型：
--
作者：
Chee, Kong Yao;Jiahao, Tom Z.;Hsieh, M. Ani
在这封信中，我们考虑的问题，推导和纳入模型预测控制（MPC）的应用程序，四旋翼控制的准确动态模型。MPC依赖于精确的动态模型来实现期望的闭环性能。然而，在复杂的系统和环境中，他们的操作不确定性的存在下，在获得足够准确的系统动态表示提出了挑战。在这封信中，我们利用深度学习工具，基于知识的神经常微分方程（KNODE），来增强从第一原理获得的模型。由此产生的混合模型包括一个名义上的第一原理模型和一个神经网络从模拟或真实世界的实验数据。使用四旋翼，我们将我们的混合模型与最先进的高斯过程（GP）模型进行基准测试，并表明混合模型提供了更准确的四旋翼动力学预测，并且能够超越训练数据进行推广。为了提高闭环性能，混合模型被集成到一个新的MPC框架，称为KNODE-MPC。结果表明，综合框架实现了60.2%的仿真和超过21%的物理实验，在轨迹跟踪性能方面的改善。
In this letter, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to quadrotor control. MPC relies on precise dynamic models to achieve the desired closed-loop performance. However, the presence of uncertainties in complex systems and the environments they operate in poses a challenge in obtaining sufficiently accurate representations of the system dynamics. In this letter, we make use of a deep learning tool, knowledge-based neural ordinary differential equations (KNODE), to augment a model obtained from first principles. The resulting hybrid model encompasses both a nominal first-principle model and a neural network learnt from simulated or real-world experimental data. Using a quadrotor, we benchmark our hybrid model against a state-of-the-art Gaussian Process (GP) model and show that the hybrid model provides more accurate predictions of the quadrotor dynamics and is able to generalize beyond the training data. To improve closed-loop performance, the hybrid model is integrated into a novel MPC framework, known as KNODE-MPC. Results show that the integrated framework achieves 60.2% improvement in simulations and more than 21% in physical experiments, in terms of trajectory tracking performance.