Elena Fersman

Towards automated service-oriented lifecycle management for 5G networks

5G networks will be a key enabler for the Internet of Things by providing a platform to connect a massive number of devices with heterogeneous sets of network quality requirements. In this environment, 5G network operators will have to solve the complex challenge of managing network services for diverse customer sectors (such as automotive, health or energy) with different requirements throughout their lifecycle. In this paper, we present current state of our work on automating part of the network service lifecycle management using knowledge management- and decision support techniques. We also present our ongoing implementation steps for such management function in 5G networks.

Concerns on the Differences Between AI and System Safety Mindsets Impacting Autonomous Vehicles Safety

The inflection point in the development of some core technologies enabled the Autonomous Vehicles (AV). The unprecedented growth rate in Artificial Intelligence (AI) and Machine Learning (ML) capabilities, focusing only on AVs, is expected to shift the transportation paradigm and bring relevant benefits to the society, such as accidents reduction. However, recent AVs accidents resulted in life losses. This paper presents a viewpoint discussion based on findings from a preliminary exploratory literature review. It was identified an important misalignment between AI and Safety research communities regarding the impact of AI on the safety risks in AV. This paper promotes this discussion, raises concerns on the potential consequences and suggests research topics to reduce the differences between AI and system safety mindsets.

Feasibility assessment to realise vehicle teleoperation using cellular networks

Future cellular networks (5G) will be used for a diversity of use cases. Transportation is one domain where cellular networks can play a significant role not only in connecting autonomous vehicles to other vehicles, infrastructures, and people, but also in realizing vehicle teleoperation i.e., vehicle driven by an operator from a distance. In this paper, we assess the feasibility of using a cellular network to realise vehicle teleoperation. We identify the network requirements for a teleoperated vehicle use case in an urban environment using a test setup of an LTE network and simulations. Testbed measurements reveal that teleoperation use cases can be supported even with less than excellent signal strength. Through simulation we show that the testbed can scale to cover greater distances and support teleoperation use cases even with background mobile broadband traffic.