IoT systems are becoming an increasingly important component of the civil and industrial infrastructure. With the growth of these IoT ecosystems, their complexity is also growing exponentially. In this paper we explore the problem of testing and evaluating large scale IoT systems at design time. To this end we employ simulated sensors with the physical and geographical characteristics of real sensors. Moreover, we propose Sensyml, a simulation environment that is capable of generating big data from cyber-physical models and real-world data. To the best of our knowledge it is the first approach to use a hybrid integration of real and simulated sensor data, that is also capable of being integrated into existing IoT systems. Sensyml is a cloud based Infrastructure-as-a-Service (IaaS) system that enables users to test both functionality and scalability of their IoT applications.
There is a huge discrepancy between off-the-shelf (COTS) hardware architectures and requirements for embedded industrial applications. Industrial systems are getting more complex by the day, and an interaction of highly diverse components within these systems is unavoidable. An implementation of such systems on COTS hardware is challenging. Platforms based on single-core CPUs is becoming limited, and use of multicore architectures yields safety risks, and overall inefficiency. Tailored architectures provide adequate service but they lack flexibility and therefore their economic justification is limited. Emerging technologies i.e., hybrid system-on-chip combined with novel architectural concepts are filling blind spots between COTS architectures and embedded industrial applications. The paper presents the implementation of an MPSoC architecture on a hybrid system-on-a-chip platform. This architecture provides unique capabilities for embedded applications, in particular, the possibility to host mixed-criticiality and cross-domain applications.
We present DeepRIoT, a continuous integration and continuous deployment (CI/CD) based architecture that accelerates the learning and deployment of a Robotic-IoT system trained from deep reinforcement learning (RL). We adopted a multi-stage approach that agilely trains a multi-objective RL controller in the simulator. We then collected traces from the real robot to optimize its plant model, and used transfer learning to adapt the controller to the updated model. We automated our framework through CI/CD pipelines, and finally, with low cost, succeeded in deploying our controller in a real F1tenth car that is able to reach the goal and avoid collision from a virtual car through mixed reality.