Research Areas

Our research spans three interconnected areas: Robot Perception & State Estimation, 3D Vision & Spatial AI, and Embodied AI & Human-Robot Interaction. See the homepage for an overview, or explore individual research pages below.

Robot Perception & State Estimation

We develop robust multi-sensor fusion algorithms for accurate robot localization and mapping. Our work covers visual-inertial odometry, LiDAR SLAM, continuous-time trajectory …

Read more

Embodied AI & Human-Robot Interaction

We enable robots to understand, interact with, and manipulate objects in open environments through vision-language-action models and hand-object interaction modeling.

Read more

3D Vision & Spatial AI

We advance 3D scene understanding through neural radiance fields, Gaussian splatting, and foundation model integration for holistic scene representation and novel view synthesis.

Read more