Florian Shkurti

Florian Shkurti is an Assistant Professor in the Department of Computer Science at the University of Toronto. His research focuses on robotics, machine learning, and computer vision, with an emphasis on imitation learning for robot control, active semi-supervised learning, and decision-making under uncertainty. He leads the Robot Vision and Learning (RVL) lab, where his group develops methods for robots to perceive, reason, and act effectively in dynamic environments. His work spans perception, planning, and control, with applications in chemistry and biology lab automation, as well as field robotics for environmental monitoring. Shkurti is also affiliated with the UofT Robotics Institute, the Vector Institute, and the Acceleration Consortium. He will be a visiting research scientist at Ai2 in Seattle during 2025-2026.

Florian Shkurti is an Associate Professor in Computer Science at the University of Toronto, specializing in Robotics, Machine Learning, Computer Vision, and Artificial Intelligence. His research focuses on advancing perception, planning, and control in complex environments through innovative methods such as open-vocabulary 3D scene graphs, multimodal 3D mapping, and differentiable simulation. He explores safety-critical reinforcement learning, adversarial scenario generation, and underwater robotics, emphasizing robustness and adaptability. His work also includes vision-based navigation, physics-based motion synthesis, and task planning over large 3D scene graphs, with applications in chemistry robotics and human motion estimation. Shkurti's contributions span both theoretical and applied domains, aiming to enhance autonomous systems through interdisciplinary approaches.