Enhancing Sample Efficiency and Uncertainty Compensation in Learning-Based Model Predictive Control for Aerial Robots
Enhancing Sample Efficiency and Uncertainty Compensation in Learning-Based Model Predictive Control for Aerial Robots
复制标题
DOI：
10.1109/iros55552.2023.10341774
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
K. Y. Chee;T. Silva;M. A. Hsieh;George Pappas
中科院分区：
文献类型：
--
作者：
K. Y. Chee;T. Silva;M. A. Hsieh;George Pappas
最近数据可用性和可靠性的提高导致了机器人系统基于学习的模型预测控制（MPC）框架的发展激增。尽管与非学习框架相比，这些框架的性能有了很大的提高，但许多框架都依赖于离线学习过程来合成动态模型。这意味着机器人在部署过程中遇到的不确定性在学习过程中没有考虑在内。另一方面，在线学习动态模型的基于学习的MPC方法计算成本很高，并且通常需要大量数据。为了减轻这些缺点，我们提出了一种新的学习增强MPC框架，将C1自适应控制的组件到基于学习的MPC。这种集成能够以样本有效的方式精确补偿匹配和不匹配的不确定性，从而提高部署期间的控制性能。在我们提出的框架中，我们提出了两个变体，并将其应用到四旋翼系统的控制。通过仿真和物理实验，我们表明，所提出的框架不仅允许合成一个准确的动态模型的飞行，但也显着提高了闭环控制性能下的大范围的时空不确定性。
The recent increase in data availability and reliability has led to a surge in the development of learning-based model predictive control (MPC) frameworks for robot systems. Despite attaining substantial performance improvements over their non-learning counterparts, many of these frameworks rely on an offline learning procedure to synthesize a dynamics model. This implies that uncertainties encountered by the robot during deployment are not accounted for in the learning process. On the other hand, learning-based MPC methods that learn dynamics models online are computationally expensive and often require a significant amount of data. To alleviate these shortcomings, we propose a novel learning-enhanced MPC framework that incorporates components from C1 adaptive control into learning-based MPC. This integration enables the accurate compensation of both matched and unmatched uncertainties in a sample-efficient way, enhancing the control performance during deployment. In our proposed framework, we present two variants and apply them to the control of a quadrotor system. Through simulations and physical experiments, we demonstrate that the proposed framework not only allows the synthesis of an accurate dynamics model on-the-fly, but also significantly improves the closed-loop control performance under a wide range of spatio-temporal uncertainties.