PhD Research Fellow in Multisensory Networked Interactions Robotics Avatars

PhD Research Fellow in Multisensory Networked Interactions with Robotics Avatars

We invite applications for position as PhD Research Fellow in Multisensory Networked Interactions with Robotics Avatars available at Department of Informatics.

The fellowship period is three years. Depending on the candidate and the teaching needs of the department, the fellowship period can be extended either for compulsory work consisting of e.g. teaching and supervision duties and research assistance up to four years.

Starting date as soon as possible.

No one can be appointed for more than one PhD Research Fellowship period at the University of Oslo.

Place of work is the Department of Informatics at Blindern, Oslo.

The PhD fellowship position is located at the Department of Informatics and is hosted jointly by the Network and Distributed Systems Research Group and the Robotics and Intelligent Systems Research Group. The research groups consist of around 30 full- and part-time faculty members and several postdoctoral researchers and PhD students. The research groups conduct research in various areas of mobile network systems, multimedia and AR/VR/XR systems, robotics and machine learning, focusing on fundamental aspects as well as on applications in multidisciplinary contexts.

This position is part of the DRIVE project, funded by the Research Council of Norway (RCN) ), focusing on brain-driven multi-sensory robotic avatars for remote collaborative physical work. The DRIVE project involves Simula Research Laboratory and University of Texas at Austin, USA, as partners. In addition, this PhD candidate will be able to participate and exploit synergies with the National AI Centre for AI and Creativity (Mish Mash), led by University of Oslo, funded by the RCN ).

The successful candidate will join the Sustainable Immersive Networking Lab (SINLAB), a multidisciplinary team working on systems that enable users to act in remote physical spaces and experience the effects of their actions through multimodal feedback (audio, video, haptics). While SINLAB addresses applications in health, industry, education, sports, entertainment and creative domains, the focus of the PhD candidate will be on remote collaborative physical work especially the real-time interaction among humans and between humans and a remote environment.

The main challenge with such networked interactions is that haptic feedback has very stringent delay requirements as low as 20 milliseconds. Therefore, performing such actions remotely with both action and reaction traversing long distances is far beyond our technical capabilities today. Even the developments in 5G and beyond networks that specifically target significant latency reductions are not sufficient due to physical as well as resource limitations.

The core research objective of this PhD is to design and evaluate “latency hiding” methods for immersive networked interactions. This involves (i) developing predictive machine learning models that forecast user actions and remote system responses across audio, video and haptic modalities, and (ii) jointly orchestrating network and computing resources to compensate for the gap between physical latency limits and human perceptual tolerances.

The work will comprise designing networking and computing architectures that integrate prediction and control algorithms, optimizing data transformations, offloading and distributed computing, and exploiting mechanisms such as network slicing and multi-access edge computing. The overarching goal is to guarantee perceptual latency budgets and to devise embodiment recovery strategies when these budgets are exceeded, enabling consistent, realistic and cognitively coherent remote physical interaction with robotic avatars.

The Faculty of Mathematics and Natural Sciences has a strategic ambition to be among Europe’s leading communities for research, education and innovation. Candidates for these fellowships will be selected in accordance with this, and expected to be in the upper segment of their class with respect to academic credentials.

Required qualifications:

• Master’s degree or equivalent in…