racecar - Rapid Automomous Complex-Environment Competing Ackermann-steering Robot 


Prerequisites: Advanced undergrads. Familiarity with Linux (Ubuntu) is a big plus. Knowledge with ROS is also useful. Simulation platform will be available prior to IAP for students to play with the programming code.

Load: 1 P.M. - 5 P.M. on Jan. 9, 11, 13, 18, 20 (Five 4-hour sessions over two weeks with competition on the final day). 

Time Outside Class: 6-10 hours per week.


 

RACECAR – Rapid Autonomous Complex-Environment Competing Ackermann-steering Robot

Modern robots tend to operate at slow speeds in complex environments, limiting their utility in high-tempo applications. In the RACECAR course, you will be tasked with pushing the boundaries of unmanned vehicle speed. Participants will work in teams of 4-5 to develop dynamic autonomy software to race a converted RC car equipped with LIDAR, two different stereo cameras, inertial sensors, and embedded processing around a large-scale, “real-world” course. Working from a baseline autonomy stack, teams will modify the software to increase platform velocity to the limits of stability. New to this year, emphasis will be placed on utilizing computer vision and machine learning to travel the course; teams will be rewarded for not operating the LIDAR. The course culminates with a timed competition to navigate a racecourse. Classes will provide lecture overviews of relevant algorithms and lab time with instructor-assisted development. Participants must attend every class and should plan on 6-10 hours per week of self-directed development. Students must have experience with software development. Past exposure to robotics algorithms and/or embedded programming will be useful.

 

Course website: http://racecar.mit.edu/

MIT News article: https://newsoffice.mit.edu/2015/students-autonomous-robots-race-mit-tunnels-0406

Sponsor(s): Lincoln Laboratory, MIT Dept. of Aero / Astro, and the Department of the Air Force under Air Force Contract FA8721-05-C-0002.  Opinions, interpretations, conclusions and recommendations are those of the author and are not necessarily endorsed by the United States Government.