Considering Ericsson’s forecast that 29 billion devices will be connected to the Internet in 2022, 18 billion being IoT (Internet of Things) devices, and the emergence of the Industrial IoT and Industry 4.0, researchers in Autonomous Real-Time Systems will be kept very busy. Their vision? To create user-friendly, self-adaptive, resilient, high-performing systems, with low latency and jitter, while being cost-effective.

A significant part of the research in this field revolves around cyber-physical systems, clouds, and cloud control. Historically, control systems have been deployed as monolithic software implementations on carefully tuned hardware, adjacent to the plants they control. This has resulted in systems that are undesirably non-modular, not easily extensible and that have limited ability to self-adapt. In contrast, feedback-based cyber-physical systems and cloud-native applications offer the prospect of greater accessibility and flexibility, as well as higher reliability and lower latencies. Furthermore, when applications are implemented in a disaggregated manner, their execution can be distributed across the system’s many nodes, migrated, and scaled to meet individual objectives as well as that of the system as a whole.

The research performed within Autonomous Real-Time Systems is to a large extent dictated by the requirements of modern society, and largely performed in close cooperation with industry (primarily Ericsson, but also Saab and Axis, for example).