Corey Montella


I use statistical and machine learning techniques to build robots that can reliably go --from here to there-- in complex and uncertain environments. Previous projects include a robotic wheelchair that can navigate outdoor urban environments autonomously, and a gliding autonomous aircraft that maps windfields and harvests energy to soar indefinitely.


Expected 2017

Lehigh University -- Bethlehem, Pennsylvania

December 2009

Carnegie Mellon University -- Pittsburgh, Pennsylvania


January 2015 - Present

Software Engineer -- Kodowa, Inc.

Kodowa is building Eve, a programming language designed to bring the power of computation to everyone -- not by making everyone a programmer but by finding a better way for us to interact with computers. On the surface, Eve is an environment a little like Excel that allows you to "program" simply by moving columns and rows around in tables. Under the covers it's a powerful database, a temporal logic language, and a flexible IDE that allows you to build anything from a simple website to complex algorithms.

August 2010 - January 2015

Research Assistant -- Lehigh University

I was part of a team of robotics researchers at Lehigh University, headed by Professor John Spletzer, where we studied mobile autonomous systems and applied robotics. My research was focused on outdoor mobile robots, including a smart autonomous wheelchair and a gliding autonomous aerial vehicle.

January 2013 - January 2015

Laboratory Assistant -- Lehigh University

This course focused on algorithms employed in mobile robotics for navigation, sensing, and estimation. Topics included common sensor systems, motion planning, robust estimation, Bayesian estimation techniques, Kalman and Particle filters, localization and mapping. My duties included directing and preparing weekly laboratory sessions, during which students used educational robot platforms to test concepts in control, computer vision, and localization.

August 2010 - May 2011

Teaching Assistant -- Lehigh University

This course was a survey of computing for students in engineering and the sciences. The course covered basic programming concepts, structures and algorithms, and their applications to solving scientific problems. My duties included teaching two recitation session a week, holding weekly office hours, proctoring exams, and grading exams and homework.


January 2015 - Present

Eve -- Kodowa, Inc.

I am currently part of a 4-person Engineering team building Eve, a new programming language based on Datalog and Functional Reactive Programming. It is a general-purpose, data-centric, and interactive language. Picture a relational spreadsheet with I/O. As the team is small, I've had my hand in aspects including language design and semantics, IDE development, and natural language processing.

April 2011 - Present

Perpetual Autonomous Flight in UAVs -- Lehigh University

Dynamic soaring is a technique whereby horizontal wind that varies in strength or direction is used to support flight. Seabirds like albatrosses are known to travel hundreds of kilometers in a single day utilizing dynamic soaring. We are investigating the possibility of using dynamic soaring techniques and solar power to generate perpetual flight of an Unmanned Aerial Vehicle (UAV) in the jet stream. My role in the project includes: systems integration between the aircraft, autopilot, and on-board computer; software integration between wind mapper, local planner, global planner, and hardware; optimal trajectory generation; and motion planning.

January 2011 - January 2015

Smart Wheelchair System -- Lehigh University

The autonomous wheelchair project is an effort to create a robust robotic wheelchair capable of navigating outdoor urban environments. My role in the project is to facilitate accurate and reliable localization and navigation. Localization is achieved through a combination of 2D and 3D LIDARs used to track salient features such as light poles and parking meters.

Autumn 2009

Gait Learning for Bipedal Robots -- Carnegie Mellon University

Developed a machine learning technique for the Aldebaran Nao humanoid robot to learn correct gaits for bipedal locomotion. Gathered ground truth training data for both good and bad walks. Trained a nearest neighbors classifier to predict the next best pose based on learned gaits to construct a new, unique walk.


Journal Publications

Refereed Conference Preceedings

Refereed Workshops





Media Coverage

Professional Activities







Honors and Awards



Point Cloud Library
● ● ● ● ●
● ● ● ● ○
● ● ● ● ○
● ● ● ● ○
● ● ● ● ○
● ● ● ● ○
● ● ● ○ ○
● ● ○ ○ ○
● ○ ○ ○ ○


Microsoft Office
Adobe Photoshop
Microsoft Windows
● ● ● ● ●
● ● ● ● ○
● ● ● ● ○
● ● ● ● ○
Adobe Premiere
Solid Works
● ● ● ○ ○
● ○ ○ ○ ○
● ○ ○ ○ ○


Machine Learning
Motion Planning
● ● ● ● ●
● ● ● ● ○
● ● ● ○ ○
● ● ● ○ ○
Robot Vision
Robot Control
● ● ● ○ ○
● ● ○ ○ ○
● ● ○ ○ ○



Website design