CCNY Robotics Lab

NEWS: In effort to compete at the 12th Annual Intelligent Ground Vehicle Competition (IGVC), the City College team (formed by Carlos Jaramillo, Sebastian Pendola, Carlos Chinchilla, and Achyut Shrestha) was able to qualify (only 17 out of 57 teams qualified). Unfortunately, CATA did not win, and it's clear that something went wrong at launch time. The team however, is still motivated to try again next year and focus on more than "perfection"...The team only worked for less than 3 months on the new system with the open-source Robotics Operating System (ROS).

CATA's software will continue development, and stable packages will start getting released as open-source software available for free download from the CCNY Robotics' git repository at:


git clone http://robotics.ccny.cuny.edu/git/ccny-ros-pkg/cata.git/


The paper entitled "Fusing Optical Flow and Stereo in a Spherical Depth Panorama Using a Single-Camera Folded Catadioptric Rig." [pdf] was nominated finalist for Best Vision Paper at the 2011 IEEE International Conference on Robotics and Automation (ICRA 2011), Shanghai, China.

Paper Authors: Igor Labutov, Carlos Jaramillo, Jizhong Xiao

Xiaochen Zhang is the winner for the best poster award (graduate student level) at 2011 Einsteins In The City (EIC2011) Conference at the City College of New York on April 14-15th 2011.

Dr. Jizhong Xiao, together with students William Morris, Igor Labutov and Carlos Jaramillo, has been selected to receive the CCNY Mentoring Award for 2011.

From CCNY's handbook:

"The award, established in 1995, will honor faculty and students in which the interaction in a mentoring relationship has resulted in extraordinary
student achievement. The award will be made to a faculty member in conjunction with an individual student or with a student team."

Ivan Dryanovski, William Morris, and Dr. Jizhong Xiao presented their work on an Open-Source Pose Estimation System for Micro-Air Vehicles at the International Conference on Robotics and Automation (ICRA2011) held on May 9~13, 2011 in Shanghai, China.. The paper [pdf] and presentation [pdf] are available for download.

The work is part of our ongoing research into 3D Perception for MAV Navigation And Mapping , which we also presented at the Micro-UAV Perception and Control workshop. You can check out our slides [pdf].

Here are some videos we presented, showing the CityFlyer build maps of buildings on the City College:

Additionally, the paper Fusing Optical Flow and Stereo in a Spherical Depth Panorama Using a Single-Camera Folded Catadioptric Rig (authors: Igor Labutov, Carlos Jaramillo, Jizhong Xiao) was selected as a Best Vision Paper Award finalist.

We've been working on a real-time pose estimation using a Kinect camera. The algorithm runs in real-time on a desktop CPU. We're using custom RGB-D feature descriptors to do the scan registration. The code works in conjunction with OpenCV and PCL, and should be properly documented and available for download soon.

The video below shows a preview of the capabilities.

The CCNY Robotics Lab has received a €7,500 spnsorship from Ascending Technologies for research in autonomous outdoor MAV navigation. The title of the prjoect is "Can Micro Aerial Vehicles (MAVs) Fly in Woods Like Birds?" and more information is available here.

We have put together a wiki page about the quadrotors, available here:

http://robotics.ccny.cuny.edu/wiki/AscTec

The wiki contains any useful information we have come across so far (via manuals, emails with AscTec, and trial-and-error) about the AscTec hardware and software. Other AscTec users are welcome to register and update the content.

We have also set a a mailing list to facilitate communication. You can view the archive through the web interface, or post/subscibe via email:

http://asctec-users.986163.n3.nabble.com/

The CCNY Robotics Lab is contributing to the development of the ROS Kinect drivers, including a depth calibration and and an example video. you can check out our preliminary results here:

From ROS news:

The CityFlyer project at the CCNY Robotics and Intelligent Systems Lab is using Ascending Technologies Pelican and Hummingbird Quadrotor helicopters to do research in 3D mapping and navigation. The Ascending Technologies platform provides a 1.6Ghz Intel Atom processor, 500 gram payload, GPS, and barometric altimeter. The CityFlyer add several sensors, including a Hokuyo URG-04LX and IMU. The Hokuyo URG has been modified to double as a laser height estimator. The CityFlyer project is able to combine data from these sensors to do indoor SLAM using GMapping.