Safety assurance of artificial intelligence-based systems: A systematic literature review on the state of the art and guidelines for future work
AVS Neto, JB Camargo, JR Almeida… - IEEE Access, 2022 - ieeexplore.ieee.org
The objective of this research is to present the state of the art of the safety assurance of
Artificial Intelligence (AI)-based systems and guidelines on future correlated work. For this …
Artificial Intelligence (AI)-based systems and guidelines on future correlated work. For this …
Polar: A polynomial arithmetic framework for verifying neural-network controlled systems
We present POLAR (The source code can be found at https://github. com/ChaoHuang2018/
POLAR_Tool. The full version of this paper can be found at https://arxiv …
POLAR_Tool. The full version of this paper can be found at https://arxiv …
Learning representation for anomaly detection of vehicle trajectories
Predicting the future trajectories of surrounding vehicles based on their history trajectories is
a critical task in autonomous driving. However, when small crafted perturbations are …
a critical task in autonomous driving. However, when small crafted perturbations are …
Polar-express: Efficient and precise formal reachability analysis of neural-network controlled systems
Neural networks (NNs) playing the role of controllers have demonstrated impressive
empirical performance on challenging control problems. However, the potential adoption of …
empirical performance on challenging control problems. However, the potential adoption of …
Computing-in-memory neural network accelerators for safety-critical systems: Can small device variations be disastrous?
Computing-in-Memory (CiM) architectures based on emerging nonvolatile memory (NVM)
devices have demonstrated great potential for deep neural network (DNN) acceleration …
devices have demonstrated great potential for deep neural network (DNN) acceleration …
Joint differentiable optimization and verification for certified reinforcement learning
Model-based reinforcement learning has been widely studied for controller synthesis in
cyber-physical systems (CPSs). In particular, for safety-critical CPSs, it is important to …
cyber-physical systems (CPSs). In particular, for safety-critical CPSs, it is important to …
Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction
Predicting the trajectories of surrounding objects is a critical task for self-driving vehicles and
many other autonomous systems. Recent works demonstrate that adversarial attacks on …
many other autonomous systems. Recent works demonstrate that adversarial attacks on …
Cloud and Edge Computing for Connected and Automated Vehicles
The recent development of cloud computing and edge computing shows great promise for
the Connected and Automated Vehicle (CAV), by enabling CAVs to offload their massive on …
the Connected and Automated Vehicle (CAV), by enabling CAVs to offload their massive on …
A tool for neural network global robustness certification and training
With the increment of interest in leveraging machine learning technology in safety-critical
systems, the robustness of neural networks under external disturbance receives more and …
systems, the robustness of neural networks under external disturbance receives more and …
Safety-Assured Design and Adaptation of Connected and Autonomous Vehicles
Abstract Design and development of connected and autonomous vehicles (CAVs) are
accompanied by a growing concern over the safety of these systems. This chapter will …
accompanied by a growing concern over the safety of these systems. This chapter will …