arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.03212cs.ROcs.SYeess.SY
收藏

面向鲁棒飞行控制的可微分移动时域估计

Differentiable Moving Horizon Estimation for Robust Flight Control

National University of Singapore(新加坡国立大学)

Bingheng Wang, Zhengtian Ma, Shupeng Lai, Lin Zhao, Tong Heng Lee

AI总结:

针对四旋翼鲁棒控制中现有估计器调参或数据需求大的问题,提出可微分移动时域估计算法,通过卡尔曼滤波递归高效算梯度、基于模型的策略梯度无真实值学习参数,可嵌入深度网络联合优化,经仿真验证有效。

摘要:

估计外部扰动并对其作出响应对四旋翼飞行器的鲁棒控制至关重要。现有估计器通常需要大量调参或借助包含真实值(ground truth)在内的大量数据进行训练,才能达到令人满意的性能。本文提出一种数据高效的可微分移动时域估计(differentiable moving horizon estimation,DMHE)算法,该算法可在线自动调整MHE参数,还能适配不同场景。我们通过推导MHE估计轨迹关于调参的解析梯度实现这一目标,支持端到端学习以完成自动调参。尤为值得注意的是,我们证明该梯度可通过Kalman filter(卡尔曼滤波器)以递归形式高效计算。此外,我们提出一种基于模型的策略梯度算法,可直接从轨迹跟踪误差中学习参数,无需真实值。所提出的DMHE还可作为层与其他深度神经网络嵌入,实现联合优化。最后,我们通过仿真验证了所提方法的有效性,测试了地面效应、方波扰动和正弦扰动等具有挑战性的场景。

英文摘要:

Estimating and reacting to external disturbances is of fundamental importance for robust control of quadrotors. Existing estimators typically require significant tuning or training with a large amount of data, including the ground truth, to achieve satisfactory performance. This paper proposes a data-efficient differentiable moving horizon estimation (DMHE) algorithm that can automatically tune the MHE parameters online and also adapt to different scenarios. We achieve this by deriving the analytical gradient of the estimated trajectory from MHE with respect to the tuning parameters, enabling end-to-end learning for auto-tuning. Most interestingly, we show that the gradient can be calculated efficiently from a Kalman filter in a recursive form. Moreover, we develop a model-based policy gradient algorithm to learn the parameters directly from the trajectory tracking errors without the need for the ground truth. The proposed DMHE can be further embedded as a layer with other deep neural networks for joint optimization. Finally, we demonstrate the effectiveness of the proposed method via simulation, where challenging scenarios such as ground effect, square-wave and sinusoidal disturbances are examined.

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。

↑