Safety-assured design and adaptation of learning-enabled autonomous systems
Future autonomous systems will employ sophisticated machine learning techniques for the
sensing and perception of the surroundings and the making corresponding decisions for …
sensing and perception of the surroundings and the making corresponding decisions for …
Know the unknowns: Addressing disturbances and uncertainties in autonomous systems
Future autonomous systems will employ complex sensing, computation, and communication
components for their perception, planning, control, and coordination, and could operate in …
components for their perception, planning, control, and coordination, and could operate in …
Towards assurance evaluation of autonomous systems
S Beland, I Chang, A Chen, M Moser… - Proceedings of the 39th …, 2020 - dl.acm.org
Due to the probabilistic and uncertain nature of learning-enabled autonomous systems, new
assurance technologies appropriate for such systems are becoming critical for their …
assurance technologies appropriate for such systems are becoming critical for their …
Verification approaches for learning-enabled autonomous cyber–physical systems
Editor's notes: Neural network control systems are often at the heart of autonomous systems.
The authors classify existing verification methods for these systems and advocate the …
The authors classify existing verification methods for these systems and advocate the …
Reasoning about safety of learning-enabled components in autonomous cyber-physical systems
We present a simulation-based approach for generating barrier certificate functions for
safety verification of cyber-physical systems (CPS) that contain neural network-based …
safety verification of cyber-physical systems (CPS) that contain neural network-based …
Energy-efficient control adaptation with safety guarantees for learning-enabled cyber-physical systems
Neural networks have been increasingly applied to control in learning-enabled cyber-
physical systems (LE-CPSs) and demonstrated great promises in improving system …
physical systems (LE-CPSs) and demonstrated great promises in improving system …
Towards a framework for safety assurance of autonomous systems
Autonomous systems have the potential to provide great benefit to society. However, they
also pose problems for safety assurance, whether fully auton-omous or remotely operated …
also pose problems for safety assurance, whether fully auton-omous or remotely operated …
[HTML][HTML] MoDALAS: addressing assurance for learning-enabled autonomous systems in the face of uncertainty
Increasingly, safety-critical systems include artificial intelligence and machine learning
components (ie, learning-enabled components (LECs)). However, when behavior is learned …
components (ie, learning-enabled components (LECs)). However, when behavior is learned …
Run-time assurance for learning-enabled systems
D Cofer, I Amundson, R Sattigeri, A Passi… - NASA Formal Methods …, 2020 - Springer
There has been much publicity surrounding the use of machine learning technologies in self-
driving cars and the challenges this presents for guaranteeing safety. These technologies …
driving cars and the challenges this presents for guaranteeing safety. These technologies …
RTA-IR: A runtime assurance framework for behavior planning based on imitation learning and responsibility-sensitive safety model
Y Peng, G Tan, H Si - Expert Systems with Applications, 2023 - Elsevier
Current research on artificial intelligence (AI) algorithms in safety–critical areas remains
extremely challenging due to their inability to be fully verified at design time. In this paper …
extremely challenging due to their inability to be fully verified at design time. In this paper …