Safe Robot Learning in Assistive Devices through Neural Network Repair
Safe Robot Learning in Assistive Devices through Neural Network Repair
复制标题
DOI：
10.48550/arxiv.2303.04431
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
K. Majd;Geoffrey Clark;Tanmay Khandait;Siyu Zhou;S. Sankaranarayanan;Georgios Fainekos;H. B. Amor
中科院分区：
文献类型：
--
作者：
K. Majd;Geoffrey Clark;Tanmay Khandait;Siyu Zhou;S. Sankaranarayanan;Georgios Fainekos;H. B. Amor
由于需要个性化和难以建模的人机交互动力学，辅助机器人设备是神经网络（NN）应用的一个特别有前途的领域。然而，基于NN的估计器和控制器可能会在先前看不见的数据点上产生潜在的不安全输出。在本文中，我们介绍了一种算法更新神经网络控制策略，以满足一组给定的正式的安全约束，同时还优化了原来的损失函数。给定一组混合整数线性约束，我们将神经网络修复问题定义为一个混合二次规划（MIQP）。在广泛的实验中，我们证明了我们的修复方法在产生安全的小腿假肢的政策的有效性。
Assistive robotic devices are a particularly promising field of application for neural networks (NN) due to the need for personalization and hard-to-model human-machine interaction dynamics. However, NN based estimators and controllers may produce potentially unsafe outputs over previously unseen data points. In this paper, we introduce an algorithm for updating NN control policies to satisfy a given set of formal safety constraints, while also optimizing the original loss function. Given a set of mixed-integer linear constraints, we define the NN repair problem as a Mixed Integer Quadratic Program (MIQP). In extensive experiments, we demonstrate the efficacy of our repair method in generating safe policies for a lower-leg prosthesis.