Safe Robot Learning in Assistive Devices through Neural Network Repair

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 da...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-03
Main Authors: Keyvan Majd, Clark, Geoffrey, Khandait, Tanmay, Zhou, Siyu, Sankaranarayanan, Sriram, Fainekos, Georgios, Heni Ben Amor
Format: Article
Language:English
Subjects:
Algorithms
Data points
Mixed integer
Neural networks
Policies
Prostheses
Quadratic programming
Repair
Robot learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422