Carnegie Mellon University Robotics Institute Newell-Simon Hall 2205 Pittsburgh, PA 15213 parag@ri.cmu.edu
I am currently a Commercialization Specialist at the NREC, which is part of the Robotics Institute of Carnegie Mellon. I graduated from CMU in 1999 with a Ph.D. in Robotics and the University of Southern California (class of '95) with a degree in Computer Engineering/Computer Science.
I'm from Milwaukee, Wisconsin, home of the cheese heads, and the Green Bay Packers!
For fun, I fly planes. Not model planes or paper planes, but the big (ok, not THAT big) metal ones. I got my private pilot certificate in June of '95. Now that I've got it however, I don't have the money or time to use it.
My research interests include computer vision and path planning for mobile
robot navigation.
My cv is available in pdf
format.
Projects
A brief description of projects I have worked on is below. For more
information, click on the project title.
Vision-Based Obstacle Detection For Riding Lawnmowers
The Toro project, based out of the Robotics Enginnering Consortium, seeks to
automate a Toro riding lawnmower, for use on golf course fairways. I am
working on vision-based obstacle detection.
Path Planning for the Cye Personal Robot
I spent four months at Probotics,
makers of the Cye robot. I worked on path planning and telepresence.
Driver-Adaptive Lane Departure Warning Systems - Thesis Work
My Ph.D. was in the area of driver modeling and lane departure warning
systems. Specifically, can a warning system which adapts to the individual
characteristics of drivers perform better (i.e., warn earlier and with fewer
false alarms) than a system which does not account for driver differences?
It turns out, the answer is yes.
Using Vision to Detect Vehicles in the Blindspot
When drivers change lanes, they normally use their side and rear-view mirrors
to ensure that there is no vehicle in their blindspot. I use a temporal
homography approach to predict what an image should look like, given vehicle
motion estimates and a flat earth assumption. This method is robust to shadows
and lane markings.
A Reduced Complexity Vision System
Here, I describe a low-cost vision system I developed to do real-time obstacle
tracking for the USC Autonomous Helicopter effort.
Publications
Ph.D. Thesis
Batavia, P. H.,
Driver Adaptive Lane Departure Warning Systems,
CMU Tech Report CMU-RI-99-25, 1999
Thesis Proposal Batavia, P. H., Driver Adaptive Warning Systems, CMU Tech Report CMU-RI-98-07, 1998
Conference Proceedings
Batavia, P. H., Nourbakhsh, I., Path Planning for the Cye Robot,, Submitted to the IEEE International Conference on Robots and Systems, 2000.
Batavia, P. H., Pomerleau, D. A., Thorpe, C. E., Predicting Lane Position for Roadway Departure Prevention, Proceedings of the IEEE Intelligent Vehicles Symposium, Stuttgart, Germany, 1998.
Batavia, P. H., Pomerleau, D. A., Thorpe, C. E., Overtaking Vehicle Detection Using Implicit Optical Flow, Proceedings of the IEEE Intelligent Transportation Systems Conference, Boston, MA, 1997.
Batavia, P. H., Lewis, M. A., Bekey, G. , A Reduced Complexity Vision System for Autonomous Helicopter Navigation, Proceedings of the 1995 IEEE Robotics and Automation Conference, Nagoya, Japan, 1995.
Tech Reports
Batavia, P. H., Pomerleau, D. A., Thorpe, C. E.,
Detecting Overtaking Vehicles With Implicit Optical Flow, CMU Tech Report CMU-RI-97-28, 1997
Batavia, P. H., Pomerleau, D. A., Thorpe, C. E., Applying Advanced Learning Algorithms to ALVINN, CMU Tech Report CMU-RI-96-31, 1996
Batavia, P. H., Lewis, M. A., Bekey, G., A Low Cost Reduced Complexity Vision System for Autonomous Robotics and cover, Institute for Robotics and Intelligent Systems Tech Report #IRIS-94-323, 1995
Unpublished
Batavia, P. H., An Annotated
Bibliography of Human Driver Models, Unpublished Report
Here are some of my favorite aviation sites:
You are the
person to wander through here...Thanks!
parag@ri.cmu.edu