Robotics Research at CVG

With our robotics research, we explore several themes:

  • 3D scene understanding from/for robot.
  • Active Perception and robot navigation.
  • Camera-only SLAM and planning for multi-robot systems.
  • How mixed-reality enables efficient teaming and interaction between humans and robots.

Publications

  • FrontierNet: Learning Visual Cues to Explore [paper]
  • Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds [paper]
  • Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization Using Geometrical Information [paper]
  • Active visual localization for multi-agent collaboration: A data-driven approach [paper]
  • A 3D Mixed Reality Interface for Human-Robot Teaming [paper] [youtube]