Using First Principles for Deep Learning and Model-Based Control of Soft Robots.
Using First Principles for Deep Learning and Model-Based Control of Soft Robots.
复制标题
使用第一原理来深入学习和基于模型的软机器人控制。
DOI：
10.3389/frobt.2021.654398
复制
发表时间：
2021
影响因子：
3.4
通讯作者：
Killpack MD
中科院分区：
文献类型：
--
作者：
Johnson CC;Quackenbush T;Sorensen T;Wingate D;Killpack MD
软机器人的基于模型的最优控制可以使柔性欠阻尼平台能够以可重复的方式操作，并有效地完成软机器人不可能完成的任务。不幸的是，开发精确的分析动力学模型的软机器人是费时，困难，容易出错。深度学习提供了一种替代建模方法，它只需要系统输入和系统状态的时间历史，可以很容易地测量或估计。然而，完全依靠经验或学习模型涉及收集大量的代表性数据，从软机器人，以模拟复杂的状态空间，这在许多情况下可能是不可行的任务。此外，如果模型不能很好地推广，则专门使用经验模型进行基于模型的控制可能会很危险。为了解决这些挑战，我们提出了一种混合建模方法，将机器学习方法与现有的第一性原理模型相结合，以提高基于采样的非线性模型预测控制器的整体性能。我们验证了这种方法在软机器人平台上，并表明，性能提高了52%，平均采用组合模型时。
Model-based optimal control of soft robots may enable compliant, underdamped platforms to operate in a repeatable fashion and effectively accomplish tasks that are otherwise impossible for soft robots. Unfortunately, developing accurate analytical dynamic models for soft robots is time-consuming, difficult, and error-prone. Deep learning presents an alternative modeling approach that only requires a time history of system inputs and system states, which can be easily measured or estimated. However, fully relying on empirical or learned models involves collecting large amounts of representative data from a soft robot in order to model the complex state space–a task which may not be feasible in many situations. Furthermore, the exclusive use of empirical models for model-based control can be dangerous if the model does not generalize well. To address these challenges, we propose a hybrid modeling approach that combines machine learning methods with an existing first-principles model in order to improve overall performance for a sampling-based non-linear model predictive controller. We validate this approach on a soft robot platform and demonstrate that performance improves by 52% on average when employing the combined model.