Runtime Verification of the ARIAC Competition: Can a Robot be Agile and Safe at the Same Time?

Published

November 27, 2020

Author(s)

Angelo Ferrando, Zeid Kootbally, Pavlo Piliptchak, Rafael Cardoso, Craig I. Schlenoff, Michael Fisher

Abstract

ARIAC (Agile Robotics for Industrial Automation Competition) is a robotic competition which aims to advance robotic agility in industry. Participants in this competition are required to implement a robot control system to overcome agility challenges in a simulated environment. ARIAC comes with a set of score metrics to evaluate the performance of each control system during task execution. In this paper we show how such task-oriented evaluation can be problematic and how the addition of runtime monitors to verify properties derived by ISO/TS standards can help in reducing the resulting reality gap.

Proceedings Title

19th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2020)

Conference Dates

November 25-27, 2020

Conference Location

Virtually, IT

Pub Type

Conferences

Download Paper

Local Download

Keywords

ARIAC, agility, robotics, safety, real-time monitoring, simulation

Citation

Ferrando, A. , Kootbally, Z. , Piliptchak, P. , Cardoso, R. , Schlenoff, C. and Fisher, M. (2020), Runtime Verification of the ARIAC Competition: Can a Robot be Agile and Safe at the Same Time?, 19th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2020), Virtually, IT, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=931511 (Accessed December 5, 2024)