학술논문

Assured Runtime Monitoring and Planning: Toward Verification of Neural Networks for Safe Autonomous Operations
Document Type
Periodical
Source
IEEE Robotics & Automation Magazine IEEE Robot. Automat. Mag. Robotics & Automation Magazine, IEEE. 27(2):102-116 Jun, 2020
Subject
Robotics and Control Systems
Aerospace
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
General Topics for Engineers
Signal Processing and Analysis
Transportation
Power, Energy and Industry Applications
Artificial neural networks
Trajectory
Safety
Runtime
Planning
Monitoring
Language
ISSN
1070-9932
1558-223X
Abstract
Autonomous systems operating in uncertain envi ronments under the effects of disturbances and noises can reach unsafe states even while using finetuned controllers and precise sensors and actuators. To provide safety guarantees on such systems during motion planning operations, reachability analysis (RA) has been demonstrated to be a powerful tool. RA, however, suffers from computational complexity, especially when dealing with intricate systems characterized by high-order dynamics, making it hard to deploy for runtime monitoring.