基于模仿与管道引导数据增强的MPC高效深度学习鲁棒策略
Efficient Deep Learning of Robust Policies from MPC using Imitation and Tube-Guided Data Augmentation
AI总结：
本文提出利用鲁棒管道MPC与数据增强，从单个MPC演示高效训练深度神经网络策略，实现对新扰动的鲁棒性和零样本迁移，在演示效率、训练时间及鲁棒性上优于DAgger和域随机化。
摘要：
模仿学习（IL）能够利用模型预测控制（MPC）提供的演示生成计算高效的策略。然而，IL方法通常需要大量的数据收集和训练工作，当任务发生变化时策略难以调整，并且生成的策略对新扰动的鲁棒性有限。在本工作中，我们提出一种IL策略，将计算代价高昂的MPC高效压缩为深度神经网络策略，并使其对未见过的扰动具有鲁棒性。通过使用MPC的一种鲁棒变体，即鲁棒管道MPC（Robust Tube MPC），并利用该控制器的性质，我们引入了计算高效的数据增强方法，从而能够显著减少生成鲁棒策略所需的MPC演示数量和训练工作。我们的方法使得从在标称域（例如仿真环境或实验室/受控环境中的机器人）中收集的单个MPC演示训练得到的策略，能够零样本迁移到具有未见过的有界模型误差/扰动的新域。使用线性和非线性MPC在多旋翼飞行器上进行敏捷飞行所开展的数值评估表明，我们的方法在演示效率、训练时间以及对训练期间未见扰动的鲁棒性方面，优于IL中常用的策略（如数据集聚合（DAgger）和域随机化（DR））。实验评估验证了该方法的效率和真实世界鲁棒性。
英文摘要：
Imitation Learning (IL) can generate computationally efficient policies from demonstrations provided by Model Predictive Control (MPC). However, IL methods often require extensive data-collection and training efforts, limiting changes to the policy if the task changes, and they produce policies with limited robustness to new disturbances. In this work, we propose an IL strategy to efficiently compress a computationally expensive MPC into a deep neural network policy that is robust to previously unseen disturbances. By using a robust variant of the MPC, called Robust Tube MPC, and leveraging properties from the controller, we introduce computationally efficient data augmentation methods that enable a significant reduction of the number of MPC demonstrations and training efforts required to generate a robust policy. Our approach opens the possibility of zero-shot transfer of a policy trained from a single MPC demonstration collected in a nominal domain, such as a simulation or a robot in a lab/controlled environment, to a new domain with previously unseen bounded model errors/perturbations. Numerical evaluations performed using linear and nonlinear MPC for agile flight on a multirotor show that our method outperforms strategies commonly employed in IL (such as Dataset-Aggregation (DAgger) and Domain Randomization (DR)) in terms of demonstration-efficiency, training time, and robustness to perturbations unseen during training. Experimental evaluations validate the efficiency and real-world robustness.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
