Active & semantic SLAM
Building meaningful representations of the world for autonomous robots. My research spans probabilistic semantic mapping, visual SLAM under challenging conditions, and active exploration with UAVs.
Related publicationsResearch directions
Perception, representation and learning for robots that operate in the real world.
Building meaningful representations of the world for autonomous robots. My research spans probabilistic semantic mapping, visual SLAM under challenging conditions, and active exploration with UAVs.
Related publicationsLearning robot behavior from observations, demonstrations and interaction. I investigate imitation learning, reinforcement learning and the use of vision-language models for robotic manipulation and human–robot interaction.
Related publicationsConnecting perception with safe decisions. I work on semantic-aware path planning, multisensor fusion, and motion prediction for navigation around people and in challenging environments.
Related publicationsTurning visual observations into useful information for robotics and inspection. Applications include monocular 3D object localization and super-resolution methods for detecting tiny defects on printed circuit boards.
Related publicationsSemantic-aware mapping and active exploration for UAVs, with research on robust visual SLAM, data association and Gaussian splatting.
Python / C++ · ROS · UAVs
Design and fabrication of a dual-arm service robot, visual 3D localization from 2D estimates and obstacle avoidance using multisensor fusion.
C++ / Python · ROS · MoveIt / Gazebo
Multi-robot collaboration, humanoid perception and interaction using vision-language and large language models, with navigation in crowded environments.
Python / C++ · ROS / ROS2
I am also interested in lifelong SLAM, robot dynamics learning, model-based reinforcement learning and learning from demonstration. Modeling uncertainty in map representations and robot dynamics is central to my interests in safe, active planning and control.
Explore the papers, implementations and demonstrations behind these research directions.