Manzoor Hussain

Manzoor Hussain, Nazakat Ali, Jang-Eui Hong

The deep neural networks (DNNs)based autonomous driving systems (ADSs) are expected to reduce road accidents and improve safety in the transportation domain as it removes the factor of human error from driving tasks. The DNN based ADS sometimes may exhibit erroneous or unexpected behaviors due to unexpected driving conditions which may cause accidents. It is not possible to generalize the DNN model performance for all driving conditions. Therefore, the driving conditions that were not considered during the training of the ADS may lead to unpredictable consequences for the safety of autonomous vehicles. This study proposes an autoencoder and time series analysis based anomaly detection system to prevent the safety critical inconsistent behavior of autonomous vehicles at runtime. Our approach called DeepGuard consists of two components. The first component, the inconsistent behavior predictor, is based on an autoencoder and time series analysis to reconstruct the driving scenarios. Based on reconstruction error and threshold it determines the normal and unexpected driving scenarios and predicts potential inconsistent behavior. The second component provides on the fly safety guards, that is, it automatically activates healing strategies to prevent inconsistencies in the behavior. We evaluated the performance of DeepGuard in predicting the injected anomalous driving scenarios using already available open sourced DNN based ADSs in the Udacity simulator. Our simulation results show that the best variant of DeepGuard can predict up to 93 percent on the CHAUFFEUR ADS, 83 percent on DAVE2 ADS, and 80 percent of inconsistent behavior on the EPOCH ADS model, outperforming SELFORACLE and DeepRoad. Overall, DeepGuard can prevent up to 89 percent of all predicted inconsistent behaviors of ADS by executing predefined safety guards.

Nazakat Ali, Manzoor Hussain, Youngjae Kim et al.

Cyber Physical Systems solve complex problems through their tight integration between the physical and computational components. Therefore, the reliability of a complex system is the most critical requirement for the cyber physical system because an unreliable system often leads to service disruption, property dam-age, financial loses and sometimes lead to fatality. In order to develop more reliable CPS, this paper proposes a generic framework for reliability modeling and analysis for our ongoing work on cyber physical systems.This paper, at first defines an architecture for general CPS which is comprised of three layers; environment layer, communication layer, and computational layer. Secondly, we formalize a reliability model for the architectural components, and then propose a framework for the reliability of CPS with the consideration of how to capture the reliability. Based on the research method, we demonstrate the proposed frame-work with an illustrative example by using different reliability values from offshore and onshore reliability data library. We confirmed that the reliability model covers almost all possible reliabilities required to general cyber-physical systems.