利用 Tube MPC 引导的数据增强高效学习鲁棒、自适应策略
Efficient Deep Learning of Robust, Adaptive Policies using Tube MPC-Guided Data Augmentation
AI总结：
本文扩展 Tube MPC 引导的模仿学习数据增强框架，利用可在线估计的低维模型/环境表示训练多旋翼自适应位置与姿态控制策略，在约1.3小时内获得强风扰动下的高精度鲁棒策略。
摘要：
在具有挑战性的非结构化环境中部署敏捷自主系统，需要具备适应能力以及对不确定性的鲁棒性。现有的鲁棒和自适应控制器（例如基于模型预测控制（MPC）的控制器）能够取得出色性能，但代价是繁重的在线机载计算。已经出现了一些从 MPC 中高效学习鲁棒且可机载部署策略的方法，但它们仍缺乏基本的适应能力。在本工作中，我们扩展了一种现有的高效模仿学习（IL）算法，用于从 MPC 学习鲁棒策略，使其能够学习适应具有挑战性的模型/环境不确定性的策略。我们方法的关键思想在于修改 IL 流程：将策略以学习到的低维模型/环境表示为条件，而该表示可以在线高效估计。我们将该方法定制用于学习自适应位置和姿态控制策略，以使多旋翼在强扰动下跟踪轨迹。仿真评估表明，可在约 1.3 小时内获得高质量的自适应策略。我们还通过实验证明其能快速适应训练分布内和分布外的不确定性：在约为机器人重量 50%、且比训练期间所见最大风力大 36% 的风扰动下，实现了 6.1 厘米的平均位置误差。
英文摘要：
The deployment of agile autonomous systems in challenging, unstructured environments requires adaptation capabilities and robustness to uncertainties. Existing robust and adaptive controllers, such as those based on model predictive control (MPC), can achieve impressive performance at the cost of heavy online onboard computations. Strategies that efficiently learn robust and onboard-deployable policies from MPC have emerged, but they still lack fundamental adaptation capabilities. In this work, we extend an existing efficient Imitation Learning (IL) algorithm for robust policy learning from MPC with the ability to learn policies that adapt to challenging model/environment uncertainties. The key idea of our approach consists in modifying the IL procedure by conditioning the policy on a learned lower-dimensional model/environment representation that can be efficiently estimated online. We tailor our approach to the task of learning an adaptive position and attitude control policy to track trajectories under challenging disturbances on a multirotor. Evaluations in simulation show that a high-quality adaptive policy can be obtained in about $1.3$ hours. We additionally empirically demonstrate rapid adaptation to in- and out-of-training-distribution uncertainties, achieving a $6.1$ cm average position error under wind disturbances that correspond to about $50\%$ of the weight of the robot, and that are $36\%$ larger than the maximum wind seen during training.
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。
