I am a third-year Ph.D. student in the Computer Vision and Geometry
Lab at ETH Zürich, working under the supervision of my advisor,
Prof. Marc Pollefeys. My current research focuses on full autonomy
for vision-guided micro aerial vehicles in both dynamic and unknown
environments. Such research entails the development of algorithms for
state estimation, visual SLAM, real-time 3D mapping, path planning,
and exploration; all these algorithms are expected to run on-board the MAV.
I was involved in the recently concluded sFly
project, and am currently involved in the V-Charge project.
I received my undergraduate degree in computer science with an
additional major in economics from Carnegie Mellon University in 2006, and
my Master's degree in computer science from Stanford University in 2007.
I am currently sponsored by the DSO Postgraduate Scholarship.
I am working on algorithms enabling automatic intrinsic and extrinsic
calibration. Accurate calibration is important for vision-guided robots.
For more details on ongoing work, check out CamOdoCal.
3D Mapping, Path Planning, and Exploration in Dynamic
I am developing algorithms that are able to run at high frequencies
onboard a MAV with limited computational resources and enable the MAV to
safely navigate cluttered indoor and urban environments with moving
objects. The MAV
builds a 3D occupancy grid that closely represents the geometrical structure
of the environment, and plans a 3D path that keeps a minimum distance from
obstacles and allows the MAV to reach its destination in the shortest
3D Reconstruction from RGBD Images
I am working on real-time techniques to build 3D structured and textured maps
using data from RGBD cameras such as stereo rigs and the Kinect. Such maps can
be used by robots for both path planning and visualization.