arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.04431cs.RO
收藏

通过神经网络修复实现辅助设备中的安全机器人学习

Safe Robot Learning in Assistive Devices through Neural Network Repair

Arizona State University(亚利桑那州立大学);University of Colorado Boulder(科罗拉多大学博尔德分校);Toyota NA-R&D(丰田北美研发中心)

Keyvan Majd, Geoffrey Clark, Tanmay Khandait, Siyu Zhou, Sriram Sankaranarayanan, Georgios Fainekos, Heni Ben Amor

AI总结:

针对神经网络控制器在辅助机器人设备上可能输出不安全动作的问题,提出将NN修复建模为MIQP,在满足形式化安全约束的同时优化原损失,并在小腿假肢实验中验证其可生成安全策略。

摘要:

辅助机器人设备因个性化需求以及难以建模的人机交互动态,成为神经网络(NN)一个特别有前景的应用领域。然而,基于NN的估计器和控制器可能会在此前未见的数据点上产生潜在不安全的输出。本文提出一种算法,用于更新NN控制策略,使其满足给定的一组形式化安全约束,同时优化原始损失函数。给定一组混合整数线性约束,我们将NN修复问题定义为一个混合整数二次规划(MIQP)。在大量实验中,我们证明了该修复方法在为小腿假肢生成安全策略方面的有效性。

英文摘要:

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.

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。

↑