Cognitive Modeling Approach for Dealing with Challenges in Cyber-Physical Systems

Abstract

In this paper, inspired by our previous works, we propose an architecture for the design and realization of cyber-physical systems (CPS) that considers the spatio-temporal context of events, promotes anomaly detection, facilitates efficient human-computer interaction and is capable of discovering novel human and/or machine knowledge. We view deep neural networks as smart sensors and sensory data from the environment represents the semantic and episodic input to a consistency seeking component of the cyber-space. Starting from a knowledge base infused with a deterministic world assumption, this module can detect anomalies and correct estimation errors by combining the outputs of multiple sensors. We also exploit an episodic description of ongoing situations by integrating temporal segmentation with kernel and low-dimensional embedding based methods. We demonstrate parts of the architecture through illustrative examples on our self-collected driving dataset. Our framework can be related to cognitive science foundations and may facilitate reliable functioning of CPS through integrating traditional AI and deep learning methods with deterministic models and reasoning tools. We expect that such knowledge base and cognition driven approaches of joining deep neural networks will be adopted in complex CPS. This looks like a scalable, and beneficial match between human knowledge and the exploding deep learning technologies.