Two School of Computer Science students were part of teams awarded 2022 Qualcomm Innovation Fellowships for their work in pose estimation and optimization in distributed deep learning. As part of the program, each team will receive $100,000 in funding and mentoring from Qualcomm engineers. Zhengyi Luo, a Ph.D. student in the Robotics Institute (RI), and Yu-Jhe Li, a Ph.D. student in the Electrical and Computer Engineering Department, are researching pose estimation, an essential component for human-like 3D avatars in games or sci-fi-like telepresence. They were nominated for their proposal "Near- and Far-Field Sensor Fusion for 3D Body Pose Estimation and Tracking," which merges the two sensing techniques and leverages the advantages of each. By fusing the two data streams, their work could enhance the quality of immersive mixed-reality experiences.

Tim has been selected for his proposal: 'A Fully Probabilistic Theory of Autonomous Decision Making'. Tim's proposal is about developing a fully probabilistic framework for reinforcement learning to provide reliable and mathematically rigorous uncertainty quantification. In contrast to previous approaches, he proposes to treat both the learning process as well as the model components, such an agent's policy, probabilistically. The approach will combine advances in probabilistic inference and modelling with probabilistic reinforcement learning. This will enable autonomous vehicles and machines to'know what they know' as well as what they don't know, and therefore to operate more safely and reliably.