Research team
Bringing wireless multi-user interactive mobile Extended Reality to the real world using Millimeter-Wave.
Abstract
Extended Reality (XR) continues to gain more traction, with an ever-expanding array of both consumer and business applications. When designing such applications, one can choose between tethered, wirelessly connected or fully standalone Head-Mounted Displays (HMDs). These result in constrained user freedom, compression artifacts, or limited visual fidelity respectively. In this project, we aim to enable a best-of-all-worlds solution, where wireless Millimeter-Wave (mmWave) links are leveraged for consistent extremely high-quality and low-latency data delivery. Current mmWave solutions behave poorly under motion, with link degradation and even interruptions being commonplace. In this project, we will investigate avenues for enabling interactive mobile multi-user XR through mmWave. Consistent room-wide coverage will require multiple Access Points (APs), so we will investigate their optimal placement along with dynamic, proactive assignment of HMDs to APs, including practical zero-latency handovers. Furthermore, we will design real-world proactive receive-side beamforming for HMDs, as to maintain consistently high-quality links during rapid rotational motion. Data rate and reliability will be improved through both current-day solutions such as MU-MIMO, and future solutions such as Reconfigurable Intelligent Surfaces and Distributed Antenna Arrays. All this will be evaluated through a novel testbed along with simulation. Testbed design and simulation tools will be open source.Researcher(s)
- Promoter: Famaey Jeroen
- Fellow: Struye Jakob
Research team(s)
Project type(s)
- Research Project
From meta-learning towards lifelong learning; efficient and fast reinforcement learning for complex environments.
Abstract
Reinforcement Learning agents have attained incredible achievements over the past few years, with AlphaGo's resounding victory over one of the world's top Go players as a crowning achievement. A severe limitation of such agents is that they only know how to function in one very specific environment; AlphaGo is unable to play Go with a tweaked ruleset, let alone play competitively in a different board game. The meta-learning principle aims to improve this. By training the agent not only on one task, but instead on many tasks from a distribution, the trained agent can quickly learn how to behave in a novel task from the distribution. In this project, we propose several improvements to the field of meta-reinforcement learning. First, we propose a meta-learner based on Hierarchical Temporal Memory, which mimics the human brain according to our current understanding of it. This system adapts quickly to changing patterns in the environment—a desirable property for a meta-learner. We also investigate a plethora of ways to auto-generate these task distributions, and evaluate how we can introduce new abilities efficiently to an already trained meta-learner. Finally, we will extend a meta-learner to work with not just one, but with many task distributions. Ideally, such a system would be able to quickly learn to perform any conceivable task at least as well as a human.Researcher(s)
- Promoter: Latré Steven
- Fellow: Struye Jakob
Research team(s)
Project type(s)
- Research Project