Safe learning with real-time constraints: a case study

Authors:
Giorgio Metta;Lorenzo Natale;Shashank Pathak;Luca Pulina;Armando Tacchella
Affiliations:
DIST, Università di Genova, Genova, Italy and Italian Institute of Technology, Genova, Italy;Italian Institute of Technology, Genova, Italy;DIST, Università di Genova, Genova, Italy;DIST, Università di Genova, Genova, Italy;DIST, Università di Genova, Genova, Italy
Venue:
IEA/AIE'10 Proceedings of the 23rd international conference on Industrial engineering and other applications of applied intelligent systems - Volume Part I
Year:
2010

Citing 11
Cited 0

Formal verification in hardware design: a survey

ACM Transactions on Design Automation of Electronic Systems (TODAES)
Model checking

Model checking
Model Checking Programs

Automated Software Engineering
Hybrid Automata: An Algorithmic Approach to the Specification and Verification of Hybrid Systems

Hybrid Systems
Lyapunov design for safe reinforcement learning

The Journal of Machine Learning Research
Development environments for autonomous mobile robots: A survey

Autonomous Robots
Editorial

International Journal of Robotics Research
Asimovian adaptive agents

Journal of Artificial Intelligence Research
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter
Hybrid systems: from verification to falsification

CAV'07 Proceedings of the 19th international conference on Computer aided verification
Improvements to the SMO algorithm for SVM regression

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Aim of this work is to study the problem of ensuring safety and effectiveness of a multi-agent robot control system with real-time constraints in the case of learning components usage. Our case study focuses on a robot playing the air hockey game against a human opponent, where the robot has to learn how to minimize opponent's goals. This case study is paradigmatic since the robot must act in real-time, but, at the same time, it must learn and guarantee that the control system is safe throughout the process. We propose a solution using automatatheoretic formalisms and associated verification tools, showing experimentally that our approach can yield safety without heavily compromising effectiveness.